© 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. 139055
    Prev
    Next
    INDEX
    Explanations

    trained, spoilers, statement, stamps, problem, mentioned, chartered

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

    place names, technical terms, common phrases

    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
     Australia
    0.55
    И
    0.52
     Biological
    0.50
     unten
    0.47
    ленд
    0.46
     Province
    0.45
     Logistic
    0.44
    textarea
    0.44
    ي
    0.44
     Donor
    0.43
    POSITIVE LOGITS
    oração
    0.51
    Hoje
    0.50
     símbolos
    0.47
     llamó
    0.47
     aconte
    0.46
     respeito
    0.46
    的神
    0.46
     possíveis
    0.45
    राई
    0.45
     puzzling
    0.44
    Activations Density 0.000%

    No Known Activations