© 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. 13-GEMMASCOPE-2-RES-65K
    7. 678
    Prev
    Next
    INDEX
    Explanations

    classification and purpose

    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_13_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
    :
    0.90
     in
    0.80
    ที่
    0.74
     คน
    0.72
     من
    0.71
     по
    0.70
    是一个
    0.70
     at
    0.69
    ,
    0.69
     แม
    0.69
    POSITIVE LOGITS
    এর
    1.24
     personable
    1.02
    sized
    1.00
    funded
    0.96
     お知らせ
    0.96
    initializer
    0.95
    ˏ
    0.95
     एग्जामपुर
    0.94
    upon
    0.93
    goers
    0.92
    Activations Density 0.513%

    No Known Activations