© 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. 78354
    Prev
    Next
    INDEX
    Explanations

    names and locations

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

    hotlines and URLs

    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
    the
    1.92
    h
    1.62
    to
    1.48
    tions
    1.30
    ty
    1.29
    t
    1.28
    The
    1.23
    ts
    1.20
    It
    1.20
    time
    1.19
    POSITIVE LOGITS
    ۹
    1.17
    ли
    1.16
    ла
    1.08
    с
    1.02
    ס
    1.00
    ۳
    0.99
     પ્રકાર
    0.98
    دين
    0.97
    ъм
    0.96
     disgraced
    0.95
    Activations Density 2.815%

    No Known Activations