© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    numbers following 1

    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
    0.39
    ing
    0.36
    s
    0.34
    ap
    0.33
    ad
    0.30
    X
    0.30
    Error
    0.30
     that
    0.29
    ar
    0.29
    ah
    0.28
    POSITIVE LOGITS
    なく
    0.34
    ι
    0.31
    発生
    0.29
    0.29
     possa
    0.28
    с
    0.28
     crédit
    0.27
     t
    0.26
     était
    0.26
     été
    0.25
    Activations Density 0.332%

    No Known Activations