© 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. 197834
    Prev
    Next
    INDEX
    Explanations

    not commodity, not entirely, Jesus tells

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

    currently. if. even. safely

    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
     CCSDT
    0.54
     聞い
    0.52
    𝕥
    0.51
     ύ
    0.50
     血
    0.50
     忄
    0.48
     アー
    0.47
     зло
    0.47
     تحليل
    0.47
     ጥ
    0.46
    POSITIVE LOGITS
    in
    0.68
    ar
    0.66
    as
    0.63
    I
    0.58
    i
    0.56
    interface
    0.54
    import
    0.53
    ind
    0.53
    Interface
    0.52
    an
    0.52
    Activations Density 0.000%

    No Known Activations