© 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. 200365
    Prev
    Next
    INDEX
    Explanations

    exceptions and eligibility restorations

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

    development and characteristics

    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
    ral
    0.52
    .
    0.48
    る
    0.47
     definit
    0.46
    amazon
    0.46
    .\"
    0.46
    บน
    0.46
     tangible
    0.45
     Amb
    0.44
     &
    0.44
    POSITIVE LOGITS
    وون
    0.46
     megfelel
    0.46
     الموسم
    0.46
    ِلِّ
    0.45
    eteries
    0.45
    Flicky
    0.45
     Exceptional
    0.45
    isValue
    0.44
    Except
    0.43
    شون
    0.42
    Activations Density 0.000%

    No Known Activations