© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 596
    Prev
    Next
    INDEX
    Explanations

    curcumin, catena, infarct, Russian, commands

    np_acts-logits-general · gemini-2.5-flash-lite

    non-English text characters and words, especially in Asian and Cyrillic scripts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    甗
    -3.14
    ’
    -3.13
     '
    -3.09
    相変わらず
    -2.72
    ఽ
    -2.61
    ごちそう
    -2.58
    很是
    -2.56
    向けの
    -2.55
    𐬹
    -2.55
     immense
    -2.53
    POSITIVE LOGITS
     If
    3.77
    If
    3.08
    榈
    2.92
    而又
    2.75
    man
    2.73
     thinks
    2.64
    It
    2.63
    櫚
    2.59
     believes
    2.59
    $
    2.58
    Activations Density 0.019%

    No Known Activations