© 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. 39035
    Prev
    Next
    INDEX
    Explanations

    Epsom salts

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

    image file extensions and code

    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
     Boga
    0.47
     acc
    0.46
     Zara
    0.45
     alfa
    0.45
     Justices
    0.45
     avant
    0.45
    é
    0.45
     Burgundy
    0.45
     Garnier
    0.44
     الله
    0.44
    POSITIVE LOGITS
    лаб
    0.52
    бай
    0.52
    ҹ
    0.49
    хід
    0.48
    要注意
    0.47
    。</
    0.46
    砶
    0.46
    读书
    0.46
     инду
    0.46
    fähig
    0.45
    Activations Density 0.000%

    No Known Activations