© 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. 43448
    Prev
    Next
    INDEX
    Explanations

    medical, legal, and sports contexts

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

    explaining perspectives and principles

    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
    ים
    0.53
     divisible
    0.46
    ો
    0.44
     credible
    0.44
     copied
    0.43
     virulent
    0.43
     eclectic
    0.43
     lucru
    0.43
    .
    0.43
     parc
    0.42
    POSITIVE LOGITS
    hko
    0.49
    kommer
    0.46
    刘
    0.46
    Timestamp
    0.46
    姆
    0.46
    গঠনিক
    0.45
    SqlServer
    0.45
    helial
    0.44
    টিক
    0.44
     কর্মকর্তার
    0.43
    Activations Density 0.000%

    No Known Activations