© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9366
    Prev
    Next
    INDEX
    Explanations

    commit murder bar exam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    σκευ
    1.29
    ුව
    1.27
    案
    1.25
     czemu
    1.23
     jas
    1.21
    델
    1.18
    appui
    1.16
     bowel
    1.16
    Configs
    1.16
    ̊
    1.15
    POSITIVE LOGITS
    ظر
    1.43
    だから
    1.33
    Econom
    1.31
     Sorry
    1.28
     Propaganda
    1.28
    Veter
    1.25
    Sorry
    1.23
     Oh
    1.23
    وعة
    1.22
     Ironically
    1.20
    Activations Density 0.020%

    No Known Activations