© 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. 228889
    Prev
    Next
    INDEX
    Explanations

    professional research and business contexts

    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
    句
    0.52
    жду
    0.50
    AUTHORIZED
    0.49
    ходят
    0.48
    ות
    0.46
     カラ
    0.46
    ΡΟ
    0.45
    利
    0.45
    大多数
    0.45
     моего
    0.45
    POSITIVE LOGITS
     Nederland
    0.46
    spers
    0.45
    riet
    0.44
    doc
    0.42
    tä
    0.42
    consumption
    0.42
     Serialize
    0.42
     Egypt
    0.42
    Been
    0.42
                             
    0.41
    Activations Density 0.000%

    No Known Activations