© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14417
    Prev
    Next
    INDEX
    Explanations

    sets of reps

    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_7_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
    妨
    1.80
    ેલા
    1.77
    iejsc
    1.72
     lesquels
    1.71
     Cnemidophorus
    1.68
     मीटिंग
    1.64
    สถานที่
    1.60
     vagas
    1.60
     skirm
    1.59
     uș
    1.58
    POSITIVE LOGITS
    `(
    1.47
    hline
    1.46
    GEBURTSDATUM
    1.38
    googleapis
    1.38
     Milk
    1.37
    opot
    1.37
    óg
    1.36
    浆
    1.32
    한강
    1.30
    getParent
    1.29
    Activations Density 0.082%

    No Known Activations