© 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. 12173
    Prev
    Next
    INDEX
    Explanations

    M, Masha, Municipal, MOC

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

    phone numbers

    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
    in
    1.02
    of
    0.91
    are
    0.86
    ak
    0.84
    p
    0.82
    were
    0.82
    க்கு
    0.75
    je
    0.73
    ai
    0.71
    iname
    0.71
    POSITIVE LOGITS
    ;
    0.83
    ↵
    0.79
    ри
    0.78
    t
    0.71
    ร
    0.70
    endoza
    0.70
    ारे
    0.67
    تے
    0.66
    ため
    0.66
    ної
    0.64
    Activations Density 0.256%

    No Known Activations