© 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. 42033
    Prev
    Next
    INDEX
    Explanations

    function names and parameters

    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
    柟
    0.64
     Weltkrieg
    0.59
    ರ್ಷ
    0.58
     Verbindung
    0.57
    儩
    0.57
    kopf
    0.56
     Lobkovic
    0.56
    甴
    0.56
    தல
    0.55
     Russische
    0.55
    POSITIVE LOGITS
     a
    0.97
     o
    0.73
     for
    0.70
     (
    0.68
     ا
    0.65
     averages
    0.65
     it
    0.64
     ο
    0.64
     al
    0.64
     assays
    0.63
    Activations Density 0.007%

    No Known Activations