© 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. 199847
    Prev
    Next
    INDEX
    Explanations

    biophysical profile, popular musical, largest number, listed in

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

    rats are, fiber optic, hungry and, competitors focus

    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
     Meyers
    0.43
     池
    0.42
    side
    0.42
    σεις
    0.42
    AsUpIndicator
    0.42
     آف
    0.41
    amme
    0.40
    <0x82>
    0.40
    اف
    0.40
    largest
    0.39
    POSITIVE LOGITS
     cadence
    0.50
    秤
    0.46
    രോധ
    0.46
     през
    0.45
     veste
    0.45
    ාවිත
    0.44
     sewing
    0.44
    तेरे
    0.44
     pasal
    0.44
     promen
    0.44
    Activations Density 0.000%

    No Known Activations