© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12657
    Prev
    Next
    INDEX
    Explanations

    I would like to know

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

    The neuron fires strongly on first-person self-references, especially the pronoun “I” and related personal declarations.

    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
    fuck
    0.68
     insane
    0.63
     fuck
    0.60
     deff
    0.60
     insanity
    0.59
    بيع
    0.59
     BREAK
    0.58
     fucking
    0.57
    உ
    0.57
     vit
    0.57
    POSITIVE LOGITS
     wondered
    1.17
     curious
    0.98
     wondering
    0.96
     궁금
    0.96
     wonder
    0.91
     Curious
    0.89
     curiosity
    0.86
    wonder
    0.85
     inquisitive
    0.84
    好奇
    0.84
    Activations Density 0.229%

    No Known Activations