© 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. 20716
    Prev
    Next
    INDEX
    Explanations

    lists items separated by punctuation

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

    Titles and lists with colons

    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
    angleOf
    0.45
    S
    0.45
    AT
    0.44
    லா
    0.42
    R
    0.40
    E
    0.39
    트로
    0.39
    CO
    0.38
     Exptl
    0.38
    স্য
    0.37
    POSITIVE LOGITS
    :...
    0.54
    :
    0.54
    ઃ
    0.51
     ప్రేక్షకు
    0.50
    ：
    0.50
     pocos
    0.47
     jaja
    0.44
     و
    0.44
    ようで
    0.44
     및
    0.44
    Activations Density 0.000%

    No Known Activations