© 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. 1072
    Prev
    Next
    INDEX
    Explanations

    average values calculated

    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
     niewiel
    1.01
    İlk
    1.00
    scatter
    1.00
     numerous
    0.97
    ้
    0.93
     неболь
    0.92
     dito
    0.91
    Enter
    0.90
     işte
    0.89
    Reform
    0.88
    POSITIVE LOGITS
    ل
    1.31
    值
    1.25
    值为
    1.22
    পড়
    1.17
    ح
    1.16
    ر
    1.05
    身高
    1.05
    ان
    1.03
    eritud
    1.01
    ﺯ
    0.99
    Activations Density 0.229%

    No Known Activations