© 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. 10360
    Prev
    Next
    INDEX
    Explanations

    function calls, lambda arguments

    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
    Sku
    0.95
     sàng
    0.94
     going
    0.93
     궁
    0.93
     afar
    0.93
    Loksatta
    0.92
     niez
    0.92
     현실
    0.91
     Mohawk
    0.91
     inim
    0.89
    POSITIVE LOGITS
    ان
    1.15
    v
    1.13
    u
    1.10
    ou
    1.07
    el
    1.04
    k
    1.04
     uwagę
    1.01
    ਏ
    1.01
    cA
    0.97
    tou
    0.97
    Activations Density 0.053%

    No Known Activations