© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3061
    Prev
    Next
    INDEX
    Explanations

    sh-ard, sh-aking, bust-ard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    -
    0.80
     cit
    0.73
     Sw
    0.71
     Hyper
    0.70
     doch
    0.70
     An
    0.70
     activ
    0.69
     dependent
    0.69
     करा
    0.69
     w
    0.69
    POSITIVE LOGITS
     sprayer
    1.03
    regator
    0.97
     saucepan
    0.94
     renovating
    0.93
     Wallpaper
    0.92
    speaker
    0.90
     kayu
    0.90
     addon
    0.89
     SPEAKER
    0.89
     storyboard
    0.89
    Activations Density 0.323%

    No Known Activations