© 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. 6299
    Prev
    Next
    INDEX
    Explanations

    account and its related functions

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

    The neuron responds to mentions of academic contexts or institutions (e.g. “Academic,” “Medical,” “Academy,” etc.).

    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
    ğin
    0.64
     Sule
    0.62
     substant
    0.61
    蛾
    0.58
     esegu
    0.57
    كذا
    0.56
     अन्त
    0.55
     Szk
    0.55
     arrière
    0.55
    Slf
    0.55
    POSITIVE LOGITS
    ancy
    0.82
    ac
    0.75
    Acc
    0.71
    Ac
    0.70
    rustic
    0.70
    ע
    0.70
     Ac
    0.69
    acia
    0.68
    acry
    0.68
    ger
    0.67
    Activations Density 0.484%

    No Known Activations