© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    getter calls

    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
     knees
    0.92
    
    0.90
    думы
    0.90
     ấy
    0.83
     twofold
    0.83
    даря
    0.82
     mercy
    0.78
    өх
    0.77
     iniziamo
    0.76
    ងឺ
    0.76
    POSITIVE LOGITS
    Geb
    0.80
    av
    0.79
    Get
    0.75
    ein
    0.75
    가
    0.72
    Av
    0.72
    Kom
    0.72
    Ž
    0.71
    in
    0.70
    제의
    0.70
    Activations Density 0.021%

    No Known Activations