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. 29-GEMMASCOPE-2-RES-65K
    4. 5951
    Prev
    Next
    INDEX
    Explanations

    any decisions

    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_29_width_65k_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
    꿉
    0.76
     plane
    0.76
    Ort
    0.75
    setId
    0.74
    boBox
    0.72
     Ort
    0.70
    plane
    0.68
     vrat
    0.68
    Barr
    0.68
    Hall
    0.68
    POSITIVE LOGITS
     Treated
    0.75
    大きく
    0.69
    ޒ
    0.69
     impoz
    0.69
     Area
    0.69
     Tulane
    0.68
     হঠাৎ
    0.67
     peduncul
    0.67
     크게
    0.67
     Gator
    0.67
    Activations Density 0.013%

    No Known Activations