© 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. 188207
    Prev
    Next
    INDEX
    Explanations

    dance steps

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

    flask, python, web app setup

    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
    ⨔
    0.57
     NPTypeCode
    0.56
     Öff
    0.53
    𒈪
    0.52
    𒅀
    0.52
    镞
    0.52
    MSFont
    0.51
     इंजन
    0.51
     создал
    0.51
     ktorý
    0.50
    POSITIVE LOGITS
    ers
    0.54
    Name
    0.49
    ,
    0.49
    ↵
    0.47
    riche
    0.45
    <0x0D>
    0.44
    <strong>
    0.44
    est
    0.44
    by
    0.43
                                   
    0.43
    Activations Density 0.000%

    No Known Activations