© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    command identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    '
    2.06
    ़
    1.95
    я
    1.91
    $
    1.82
    ted
    1.77
    .
    1.73
    ’
    1.68
    a
    1.53
    器
    1.49
    ла
    1.46
    POSITIVE LOGITS
    upaten
    1.60
    سازی
    1.59
    जैसे
    1.51
    งิน
    1.48
     νέ
    1.48
    ற்போது
    1.46
    देखिए
    1.43
     slučaju
    1.40
    ‖
    1.40
    elni
    1.39
    Activations Density 0.629%

    No Known Activations