© 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. 244563
    Prev
    Next
    INDEX
    Explanations

    Brandon Marshall

    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
     :,
    0.51
    yu
    0.50
     cucumber
    0.50
    etag
    0.49
    y
    0.49
     curd
    0.47
    T
    0.46
    Cucumber
    0.45
     स्किप
    0.45
     -,
    0.45
    POSITIVE LOGITS
    lections
    0.47
    이에
    0.46
    ائن
    0.46
    ثال
    0.46
    糬
    0.46
    ם
    0.45
     referência
    0.45
    лимп
    0.44
    䐍
    0.44
    وله
    0.42
    Activations Density 0.000%

    No Known Activations