© 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. 13024
    Prev
    Next
    INDEX
    Explanations

    Download lagu

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

    language and technical terms

    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
    및
    0.52
    İY
    0.45
    ii
    0.44
     বিষয়ক
    0.44
    ë
    0.44
    ylobacter
    0.44
    alı
    0.43
    II
    0.43
    archiviato
    0.43
    کیل
    0.43
    POSITIVE LOGITS
     phare
    0.63
     koja
    0.62
     S
    0.61
     which
    0.59
     ط
    0.59
     E
    0.58
     J
    0.57
     التي
    0.57
     F
    0.56
     Б
    0.56
    Activations Density 0.017%

    No Known Activations