© 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. 126271
    Prev
    Next
    INDEX
    Explanations

    outrageous, strengths, cast, difference

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

    CEO fraud scam

    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
    static
    0.52
    ra
    0.48
    以及
    0.47
    ="",
    0.46
    inline
    0.46
    override
    0.46
    to
    0.45
    atto
    0.45
    labs
    0.45
    =""
    0.44
    POSITIVE LOGITS
     mình
    0.52
     financiar
    0.48
     moan
    0.48
     bekommen
    0.47
     Versicher
    0.47
     treba
    0.47
     impatience
    0.47
     औरत
    0.46
     Comrade
    0.46
     prvo
    0.46
    Activations Density 0.003%

    No Known Activations