© 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. 19943
    Prev
    Next
    INDEX
    Explanations

    Haskell IO monad

    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
    де
    1.11
    ে
    0.87
    ки
    0.86
    ي
    0.85
    開始
    0.82
    that
    0.81
    га
    0.79
    ма
    0.79
    ти
    0.78
    ্ড
    0.77
    POSITIVE LOGITS
    v
    0.85
     ::
    0.80
    ח
    0.80
     apple
    0.79
    س
    0.77
     equine
    0.75
     angios
    0.75
     êtres
    0.74
     beige
    0.72
     pectin
    0.72
    Activations Density 0.001%

    No Known Activations