© 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. 39670
    Prev
    Next
    INDEX
    Explanations

    making seams, arrays, strips

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

    drawing lines slowly

    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
    /*
    0.54
    ,
    0.49
    ,*
    0.45
    ,%
    0.43
    ,&
    0.43
    7
    0.43
    sst
    0.42
    ρθ
    0.42
     MANY
    0.42
     ALSO
    0.42
    POSITIVE LOGITS
     በኋላ
    0.47
     determinato
    0.47
     ሂደት
    0.47
    Tangent
    0.47
    嘤
    0.46
     ဖ
    0.46
    คองโก
    0.45
     giocatori
    0.45
    ூட்
    0.45
    慵
    0.45
    Activations Density 0.000%

    No Known Activations