© 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. 236242
    Prev
    Next
    INDEX
    Explanations

    plugin immediately arises

    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
    Kenneth
    0.44
    堯
    0.44
    🌡
    0.43
    OZ
    0.42
    ０
    0.42
    тити
    0.42
    $，
    0.42
    邢
    0.42
    Oz
    0.40
    忌
    0.40
    POSITIVE LOGITS
     ahí
    0.54
     esse
    0.53
     taea
    0.52
     essa
    0.52
     '
    0.52
     dwóch
    0.52
     torno
    0.50
     loco
    0.50
     该
    0.50
     logistical
    0.50
    Activations Density 0.001%

    No Known Activations