© 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. 9331
    Prev
    Next
    INDEX
    Explanations

    drawing in code

    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
    s
    0.87
     dry
    0.77
     discretionary
    0.75
    ل
    0.75
     insurance
    0.73
     circles
    0.72
     supplementary
    0.72
     female
    0.72
     শ্রীল
    0.72
     left
    0.70
    POSITIVE LOGITS
    類似
    0.94
    嬂
    0.93
    ጷ
    0.91
    㡚
    0.89
    깆
    0.89
    Biblioteca
    0.88
    訸
    0.88
    <unused382>
    0.87
    तलब
    0.87
     دیگر
    0.86
    Activations Density 0.002%

    No Known Activations