© 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. 5856
    Prev
    Next
    INDEX
    Explanations

    book titles and themes

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

    book titles and descriptions

    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
    ली
    0.41
     fáb
    0.40
    ه‌
    0.40
    ラ
    0.40
    ラジオ
    0.39
    ز
    0.38
    ka
    0.38
     robbers
    0.38
    ین
    0.37
    ド
    0.36
    POSITIVE LOGITS
     A
    0.67
     The
    0.63
     How
    0.60
     WITH
    0.58
     व्हाट
    0.56
     An
    0.53
     लेकिन
    0.52
    <unused619>
    0.52
     What
    0.50
     안녕하세요
    0.49
    Activations Density 0.002%

    No Known Activations