© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    pieces and quantities

    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
     reduziert
    0.84
    candles
    0.84
    Gift
    0.79
    Ble
    0.77
    S
    0.77
    lots
    0.77
    豊富
    0.77
    Give
    0.76
    osseum
    0.76
    width
    0.74
    POSITIVE LOGITS
     (!)
    0.98
     개의
    0.94
     हसीना
    0.94
    (!)
    0.92
     μή
    0.91
    смотря
    0.90
    .
    0.90
    চূ
    0.87
    .[[
    0.86
     მათ
    0.86
    Activations Density 0.019%

    No Known Activations