© 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. 80379
    Prev
    Next
    INDEX
    Explanations

    privilege to, trench or, grade access

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

    shipping and purchases

    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
     pronounced
    0.55
     deepening
    0.53
     an
    0.51
    O
    0.49
     ia
    0.48
    ྨ
    0.47
     sounds
    0.46
    anch
    0.46
     WEIGHT
    0.46
     fro
    0.46
    POSITIVE LOGITS
     بيد
    0.53
     футбо
    0.50
     виде
    0.50
     ойнотуу
    0.50
    🏸
    0.48
     очередной
    0.47
     бою
    0.46
     أكبر
    0.46
     produzido
    0.46
    يده
    0.46
    Activations Density 0.000%

    No Known Activations