© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 680
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ↵↵
    0.72
    ,
    0.71
     grieving
    0.71
     queer
    0.70
     ideological
    0.70
     Boolean
    0.69
    主动
    0.69
    .
    0.68
     آشنا
    0.67
     emotion
    0.67
    POSITIVE LOGITS
     yaklaşık
    1.75
     estimated
    1.72
     ಸುಮ
    1.71
     Approx
    1.70
     whopping
    1.70
     approximately
    1.68
     Approximately
    1.68
    approximately
    1.66
     aproximativ
    1.66
     approx
    1.66
    Activations Density 5.644%

    No Known Activations