© 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. 94892
    Prev
    Next
    INDEX
    Explanations

    following lists of words

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

    role completion

    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
    بت
    0.46
    s
    0.43
     ´
    0.42
     ва
    0.41
     Krankenhaus
    0.41
    ش
    0.41
     `
    0.39
     الهم
    0.39
    ша
    0.39
     Desert
    0.39
    POSITIVE LOGITS
    cited
    0.54
     പതി
    0.53
    ଢ
    0.52
     splike
    0.50
    øg
    0.49
    ihe
    0.49
     sakta
    0.48
    ಶ್ಚ
    0.47
     customarily
    0.47
    ált
    0.47
    Activations Density 0.000%

    No Known Activations