© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4077
    Prev
    Next
    INDEX
    Explanations

    LaTeX list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ן
    1.72
    がいる
    1.56
    elolaan
    1.53
    
    1.49
     تعالى
    1.43
     laureate
    1.43
    é
    1.42
    <bos>
    1.40
    ^{*}}\
    1.39
     síndrome
    1.38
    POSITIVE LOGITS
    s
    2.47
    t
    1.86
    ur
    1.85
    re
    1.82
    time
    1.79
    tt
    1.78
    től
    1.76
    ل
    1.74
    ット
    1.73
    ное
    1.73
    Activations Density 0.001%

    No Known Activations