© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18364
    Prev
    Next
    INDEX
    Explanations

    ΔU = Q - W; censorship; evaluates; evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    माटर
    0.46
    λή
    0.46
    сий
    0.46
    晔
    0.46
    メル
    0.45
     Возможно
    0.45
    ラク
    0.45
     grave
    0.44
     getroffen
    0.44
    ラーメン
    0.44
    POSITIVE LOGITS
    bs
    0.53
    in
    0.52
    that
    0.52
    yo
    0.49
    :
    0.48
    at
    0.48
    doo
    0.48
    റായി
    0.48
    kk
    0.48
    as
    0.47
    Activations Density 0.001%

    No Known Activations