© 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. 91608
    Prev
    Next
    INDEX
    Explanations

    projects completed and systems convey

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

    metabolism, dosage, cities across, languages

    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
     realising
    0.42
    ت
    0.42
    ST
    0.40
     jib
    0.40
    I
    0.40
     Immutable
    0.40
    Dio
    0.38
     realisation
    0.38
    Kim
    0.38
     funders
    0.38
    POSITIVE LOGITS
     以及
    0.55
     autorizado
    0.52
     éd
    0.52
    ünün
    0.51
    および
    0.50
    uose
    0.50
    りと
    0.50
    उद्योग
    0.49
    ൮
    0.49
    执法
    0.49
    Activations Density 0.003%

    No Known Activations