© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    closing code punctuation

    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
    à
    0.66
    2
    0.63
    ung
    0.59
    ø
    0.57
    and
    0.56
    ati
    0.55
    ul
    0.54
    ada
    0.54
    ena
    0.54
     and
    0.53
    POSITIVE LOGITS
    ه
    0.68
    a
    0.63
    ت
    0.56
    의
    0.50
    هي
    0.49
    ваме
    0.49
    y
    0.48
    る
    0.48
    েরই
    0.48
     底
    0.48
    Activations Density 0.231%

    No Known Activations