© 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. 99934
    Prev
    Next
    INDEX
    Explanations

    service, oil, Scout

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

    lists, definitions, and clarifications

    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
    و
    0.50
     treble
    0.46
     adherents
    0.46
    7
    0.44
     argues
    0.43
     detract
    0.43
     sculptural
    0.42
     geometri
    0.42
     flatness
    0.41
     letzte
    0.41
    POSITIVE LOGITS
     服务
    0.54
    鐩
    0.49
    JM
    0.48
     Уда
    0.48
     বিচারের
    0.48
    fitrión
    0.48
     类
    0.48
    ahua
    0.47
     Така
    0.47
     FAMILY
    0.47
    Activations Density 0.005%

    No Known Activations