© 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. 31911
    Prev
    Next
    INDEX
    Explanations

    semester began, holds information, leadership

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

    vast library of template tags

    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
    points
    0.53
     Exeter
    0.47
    ла
    0.47
    ل
    0.47
     elektr
    0.47
    Points
    0.46
     Electric
    0.46
    ونه
    0.46
     सर्जन
    0.46
    älj
    0.46
    POSITIVE LOGITS
     divent
    0.51
     abbastanza
    0.49
     prawie
    0.49
    <unused2175>
    0.48
    釟
    0.47
    聸
    0.47
     около
    0.46
    成為
    0.45
     близько
    0.45
    聁
    0.45
    Activations Density 0.000%

    No Known Activations