© 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. 126227
    Prev
    Next
    INDEX
    Explanations

    common outcomes following events

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

    names, roles, or entities

    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
     DIFF
    0.54
     SEP
    0.49
    сть
    0.47
    人們
    0.46
     FAVOR
    0.46
    ᅨ
    0.46
     CSS
    0.44
    <0x97>
    0.44
    種類
    0.44
    cussions
    0.44
    POSITIVE LOGITS
     هناك
    0.45
     كم
    0.44
     كثير
    0.43
     ნაკ
    0.42
     пределах
    0.41
     زیادی
    0.41
     Notas
    0.41
    مس
    0.41
     அங்க
    0.40
     креди
    0.40
    Activations Density 0.001%

    No Known Activations