© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    specific terms like Professor, Niño, GPT

    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
     данни
    0.57
     మరియు
    0.56
     গমন
    0.54
    <unused1047>
    0.52
    ↵↵
    0.51
     ਅਤੇ
    0.50
     ولی
    0.49
     وطالبات
    0.47
     adhipp
    0.46
    䟧
    0.46
    POSITIVE LOGITS
    е
    0.67
     you
    0.64
    k
    0.64
    О
    0.64
     they
    0.64
    _
    0.63
     that
    0.61
    de
    0.59
     t
    0.58
    о
    0.58
    Activations Density 2.230%

    No Known Activations