© 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. 58233
    Prev
    Next
    INDEX
    Explanations

    keywords, decorators, 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
    摂取
    0.49
    (
    0.47
    動力
    0.44
    いた
    0.44
    状況
    0.43
    洗濯
    0.43
    図
    0.42
    ろう
    0.42
     Diabetes
    0.42
    地震
    0.41
    POSITIVE LOGITS
     sizzling
    0.51
     অবা
    0.51
     assistants
    0.49
    appList
    0.49
     dapp
    0.48
    APPED
    0.48
    ToRemove
    0.47
     טוב
    0.46
    ğunu
    0.45
     என்று
    0.45
    Activations Density 0.000%

    No Known Activations