© 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. 53972
    Prev
    Next
    INDEX
    Explanations

    attributes and descriptions

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

    code editing and configuration

    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
    ,'"
    0.48
    /,
    0.46
    /',
    0.45
    innerText
    0.43
    ®,
    0.43
    ništ
    0.43
     भटक
    0.42
    followfollow
    0.42
     /**@
    0.42
    ′,
    0.42
    POSITIVE LOGITS
     étendue
    0.55
    大部分
    0.44
     tractable
    0.44
    فر
    0.43
     anglais
    0.43
     soph
    0.42
     attaque
    0.42
     dobu
    0.42
    Want
    0.41
    Explanation
    0.41
    Activations Density 0.000%

    No Known Activations