© 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. 128492
    Prev
    Next
    INDEX
    Explanations

    destroyed by, long footnote, Taron Egerton, All rights

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

    striking, impressive, patterns

    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
     Premises
    0.52
    קס
    0.50
    좋
    0.48
     Origins
    0.48
     Colours
    0.48
     Cái
    0.47
    Ĥ
    0.47
     Height
    0.46
    鋆
    0.46
     Ekonom
    0.46
    POSITIVE LOGITS
    ver
    0.54
    co
    0.50
    ant
    0.50
    延伸
    0.48
    ar
    0.47
     прошед
    0.47
     заявление
    0.47
    ed
    0.46
    support
    0.46
    o
    0.46
    Activations Density 0.001%

    No Known Activations