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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8034
    Prev
    Next
    INDEX
    Explanations

    telling jokes or discussing SIPs

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

    This neuron activates on longer, multi‐syllable content words.

    oai_token-act-pair · o4-miniTriggered 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
    oliberal
    0.59
    ുകൊണ്ട
    0.53
    允许
    0.52
     Lehman
    0.51
    帮你
    0.51
    doi
    0.50
    allowing
    0.49
     <?=
    0.49
    允許
    0.49
    큘
    0.49
    POSITIVE LOGITS
     excites
    1.71
    吸引
    1.52
     irritate
    1.49
     excite
    1.48
     frighten
    1.46
     fascin
    1.45
     bothers
    1.41
     attracts
    1.38
     inspires
    1.35
     impresses
    1.35
    Activations Density 0.742%

    No Known Activations