© 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. 104800
    Prev
    Next
    INDEX
    Explanations

    number and specific nouns

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

    small amount or degree

    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
     européenne
    0.45
    彻
    0.44
    あるいは
    0.44
    abdominal
    0.43
     arasındaki
    0.42
     розташо
    0.42
     রাজনৈতিক
    0.42
    evoluzione
    0.42
    ทรวง
    0.42
    >("
    0.42
    POSITIVE LOGITS
     hama
    0.47
     Dhan
    0.47
     jolly
    0.46
     peeps
    0.45
    快樂
    0.44
     Gaur
    0.44
     Luck
    0.43
     Happy
    0.43
     Avon
    0.43
     వారు
    0.42
    Activations Density 0.002%

    No Known Activations