© 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. 143409
    Prev
    Next
    INDEX
    Explanations

    stolen information or past claims

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

    Start with requirements

    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
     باقي
    0.49
    一身
    0.47
    טי
    0.46
     prenant
    0.46
    𝘶
    0.45
    饿
    0.45
    难以
    0.44
     بابا
    0.44
    ü
    0.44
     razum
    0.44
    POSITIVE LOGITS
     Wing
    0.50
     Age
    0.47
     Ha
    0.46
     dùng
    0.46
    чів
    0.46
     Kepler
    0.45
    lar
    0.44
     Marissa
    0.44
     larvae
    0.44
     Kate
    0.44
    Activations Density 0.000%

    No Known Activations