© 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. 76845
    Prev
    Next
    INDEX
    Explanations

    Dr. or credentials

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

    casinos, king, pint

    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
    ו
    0.50
     აღ
    0.45
    و
    0.45
    ({\
    0.44
    メディア
    0.44
    の原因
    0.43
    時
    0.43
     roja
    0.43
    ],\
    0.42
    ുക
    0.42
    POSITIVE LOGITS
     north
    0.44
    ings
    0.43
    ssystem
    0.43
     systems
    0.43
    king
    0.43
     electrification
    0.42
     aluminium
    0.41
    ्यूशन
    0.41
     Hedge
    0.40
    osa
    0.40
    Activations Density 0.001%

    No Known Activations