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-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3676
    Prev
    Next
    INDEX
    Explanations

    <!DOCTYPE html>

    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_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
    웁
    0.74
    uckoo
    0.73
     می‌توان
    0.69
     Claus
    0.68
     blurry
    0.68
     uncle
    0.67
    斉
    0.66
     clapping
    0.65
    รัส
    0.65
    ranking
    0.64
    POSITIVE LOGITS
     économ
    0.80
     compreender
    0.75
     सीट
    0.74
     perioada
    0.71
    ણો
    0.71
    ﺓ
    0.71
     lesquelles
    0.69
     Anyways
    0.68
    чити
    0.68
    四个
    0.68
    Activations Density 0.011%

    No Known Activations