© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    traffic alerts

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

    sharing user conversations

    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
     Wię
    0.44
    ٹرز
    0.42
    сії
    0.42
     Transportation
    0.41
     Netzwerk
    0.39
     Atau
    0.39
    聽
    0.38
     روشن
    0.38
     don
    0.38
     oder
    0.38
    POSITIVE LOGITS
    雒
    0.47
     allowNull
    0.45
    🛌
    0.44
    🥪
    0.44
    🏯
    0.44
     옳은
    0.43
    🛶
    0.43
    ອາຫານ
    0.42
    棂
    0.41
    🍛
    0.41
    Activations Density 0.000%

    No Known Activations