© 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. 59390
    Prev
    Next
    INDEX
    Explanations

    exporting, importing, supplying

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

    rumored or limited

    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
    s
    0.55
    y
    0.52
    object
    0.50
     uint
    0.50
     nya
    0.48
    Nel
    0.47
    un
    0.46
     park
    0.46
    RAR
    0.46
    Men
    0.45
    POSITIVE LOGITS
    凭借
    0.52
    နှစ်
    0.47
    スケジュール
    0.47
     கிறிஸ்து
    0.46
     الاعت
    0.45
    仞
    0.45
    леп
    0.45
    刊行
    0.45
    граф
    0.44
    ivní
    0.44
    Activations Density 0.000%

    No Known Activations