© 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. 179792
    Prev
    Next
    INDEX
    Explanations

    recommended, multiple, coloured, which, visitor, himself, first

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

    checking for errors

    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
     evaded
    0.50
     örnek
    0.47
     দূরের
    0.47
     pj
    0.46
     ଓ
    0.45
     পাক
    0.45
    桫
    0.45
    کھ
    0.45
     Rotating
    0.45
    KUR
    0.44
    POSITIVE LOGITS
    olom
    0.53
    álisis
    0.47
    il
    0.47
    ificação
    0.46
    blos
    0.43
    arlos
    0.43
    ocompat
    0.43
    Wells
    0.43
    富
    0.43
    lys
    0.42
    Activations Density 0.001%

    No Known Activations