© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 660
    Prev
    Next
    INDEX
    Explanations

    qualitative states and escalation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on words expressing joyful, uplifting, or positive sentiments (especially religious or celebratory terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    positive emotional and spiritual language, particularly related to religious themes, virtues, and uplifting sentiments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language expressing strong, affective sentiment—often faith-oriented and communal—especially positive spiritual or emotional themes.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $\
    0.58
     JSON
    0.54
     предусматри
    0.54
     предусмотре
    0.53
     DBMS
    0.53
     rudimentary
    0.52
     XML
    0.51
     établ
    0.51
     அமைக்க
    0.51
     $[\
    0.50
    POSITIVE LOGITS
    满满
    0.84
    不已
    0.82
    无比
    0.79
    💕
    0.76
    ingly
    0.75
    💗
    0.75
    💫
    0.75
    fully
    0.75
    filled
    0.74
     joie
    0.74
    Activations Density 0.958%

    No Known Activations