© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 1316
    Prev
    Next
    INDEX
    Explanations

    additional, extra, parallel, multi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    0.56
     be
    0.47
     were
    0.46
    ist
    0.46
    ک
    0.45
     you
    0.43
    c
    0.43
    _
    0.42
    ale
    0.41
    kom
    0.41
    POSITIVE LOGITS
    ﺖ
    0.59
    ς
    0.48
    ET
    0.47
    т
    0.46
    ﺕ
    0.45
    AT
    0.45
    GAS
    0.45
    FBSDKInternal
    0.45
    ATR
    0.44
     двадцать
    0.44
    Activations Density 0.293%

    No Known Activations