© 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. 149024
    Prev
    Next
    INDEX
    Explanations

    this clay

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

    key points or concepts

    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
    انی
    0.60
    Elena
    0.52
    щини
    0.49
    SERT
    0.48
    帰り
    0.47
    PROM
    0.47
    ३
    0.46
    રી
    0.46
    чика
    0.46
    atica
    0.46
    POSITIVE LOGITS
     marketable
    0.50
     biển
    0.46
     bullion
    0.46
     pastel
    0.45
     typeface
    0.44
     Steelers
    0.44
     Napa
    0.43
     relegated
    0.43
     nghề
    0.43
     Naut
    0.43
    Activations Density 0.002%

    No Known Activations