© 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. 79481
    Prev
    Next
    INDEX
    Explanations

    bone graft

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

    numerical or online activities

    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
    אר
    0.43
     indulge
    0.43
    投資
    0.41
    ாது
    0.41
    ގ
    0.41
     risultato
    0.41
     repressive
    0.39
     prace
    0.39
     responsabilità
    0.39
     imprend
    0.39
    POSITIVE LOGITS
    ACON
    0.52
     इंग्र
    0.47
    omyces
    0.46
     FULLER
    0.46
     ("
    0.46
     I
    0.46
     ASP
    0.45
    िटेशन
    0.45
     মাধ
    0.45
     accessor
    0.45
    Activations Density 0.001%

    No Known Activations