© 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. 64587
    Prev
    Next
    INDEX
    Explanations

    massive product or merchandise

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

    baker , Port , lease , walking

    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
    HttpRequest
    0.52
    kých
    0.52
    코
    0.52
     empec
    0.49
    رج
    0.49
    ረጃ
    0.48
    ड
    0.48
    ЕВ
    0.47
    رق
    0.47
    정
    0.46
    POSITIVE LOGITS
     United
    0.54
     Mann
    0.54
     Belfast
    0.54
     Military
    0.53
     Grad
    0.52
     New
    0.52
     Bus
    0.52
     Guildford
    0.52
     Byrd
    0.51
     International
    0.50
    Activations Density 0.000%

    No Known Activations