© 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. 184723
    Prev
    Next
    INDEX
    Explanations

    specified recipe

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

    park destinations

    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
     thấy
    0.50
     Secretaría
    0.49
     Обще
    0.49
    كينا
    0.47
     División
    0.46
     死
    0.46
    ؤس
    0.45
    டுக்க
    0.45
    ροσ
    0.45
    يريا
    0.44
    POSITIVE LOGITS
    s
    0.62
    u
    0.55
    in
    0.53
    papers
    0.51
    TON
    0.48
    ah
    0.47
    mum
    0.47
    are
    0.47
    sing
    0.47
    Html
    0.46
    Activations Density 0.000%

    No Known Activations