Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3732
    Prev
    Next
    INDEX
    Explanations

    variable assignments and returns

    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_22_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
    `${
    0.90
     `${
    0.83
     postoji
    0.76
    ঽ
    0.74
     nameof
    0.73
    并非
    0.73
    lbrakk
    0.72
    佲
    0.72
     خۆ
    0.71
    嵃
    0.70
    POSITIVE LOGITS
     clinging
    0.76
     strained
    0.75
    
    0.71
     sweating
    0.68
    led
    0.68
     muscular
    0.68
    &#
    0.67
    ric
    0.66
    ä
    0.66
    bye
    0.65
    Activations Density 0.176%

    No Known Activations