© 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. 112436
    Prev
    Next
    INDEX
    Explanations

    non-English characters and varied scripts

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

    story, focusing, struggle

    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
     solar
    0.50
    ᅬ
    0.49
     widespread
    0.48
     blinds
    0.48
    at
    0.47
     FRANCE
    0.46
     greenhouses
    0.45
     tanks
    0.45
     fiber
    0.45
     range
    0.45
    POSITIVE LOGITS
     އ
    0.49
    BeforeText
    0.49
    駐
    0.49
     тип
    0.46
     উপভোগ
    0.46
    fadeOut
    0.45
     chega
    0.45
    上演
    0.44
     existente
    0.44
     చూప
    0.44
    Activations Density 0.000%

    No Known Activations