© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76949
    Prev
    Next
    INDEX
    Explanations

    public sector reports

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

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    库
    0.45
    cookieParser
    0.44
     জানি
    0.42
     энергети
    0.42
     центре
    0.42
     Дру
    0.42
    かもしれない
    0.42
    中央
    0.41
    就不
    0.41
     আচ্ছা
    0.41
    POSITIVE LOGITS
    elina
    0.46
    attack
    0.45
     fortnight
    0.45
    ∑
    0.45
    Xt
    0.45
     affront
    0.44
    ashions
    0.44
    شوند
    0.44
     toned
    0.43
     erections
    0.43
    Activations Density 0.000%

    No Known Activations