© 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. 109315
    Prev
    Next
    INDEX
    Explanations

    functional parts and permissions

    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
    ed
    0.52
    _
    0.49
    '
    0.47
    ᱓
    0.47
     menacing
    0.46
    ibid
    0.46
    forgot
    0.46
    働く
    0.45
    d
    0.43
     Cinema
    0.43
    POSITIVE LOGITS
    犍
    0.57
    ář
    0.55
    ()");
    0.52
     garner
    0.52
     Dungeon
    0.50
    Root
    0.49
     և
    0.48
     явления
    0.48
     ቦ
    0.48
     Derbyshire
    0.48
    Activations Density 0.000%

    No Known Activations