© 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. 188679
    Prev
    Next
    INDEX
    Explanations

    ceramic coating

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

    callback function

    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
     życia
    0.54
     américaine
    0.53
     familiale
    0.52
     respond
    0.52
    [,,"
    0.51
     emocional
    0.50
    ច្រើន
    0.50
     berangkat
    0.50
     décide
    0.49
     incompatible
    0.49
    POSITIVE LOGITS
    t
    0.48
    down
    0.45
    Along
    0.45
    )
    0.45
    ern
    0.44
    <u>
    0.43
    Down
    0.43
    iat
    0.43
    iar
    0.43
    ش
    0.43
    Activations Density 0.001%

    No Known Activations