© 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. 251860
    Prev
    Next
    INDEX
    Explanations

    diviana, help him, states' regulations, using our, relax in, soak in, not infringe, could soon, fantastic lesson ideas

    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
    жде
    0.49
    ﾍ
    0.47
     negativ
    0.46
    被迫
    0.46
    herr
    0.46
    letak
    0.46
     pener
    0.45
     uncontroll
    0.44
    besar
    0.44
    น
    0.43
    POSITIVE LOGITS
     Owner
    0.46
     Chicago
    0.45
     Within
    0.45
     Charlottesville
    0.45
    或其他
    0.44
     Seattle
    0.44
     नामक
    0.44
     باستخدام
    0.44
    .}$
    0.44
    用い
    0.44
    Activations Density 0.000%

    No Known Activations