© 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. 22-GEMMASCOPE-2-RES-16K
    7. 585
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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_22_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
    ९
    1.04
     multipliers
    0.98
    不同的
    0.95
    ८
    0.94
    fifths
    0.94
     laaj
    0.93
     generations
    0.92
     ages
    0.91
     distintos
    0.90
     depths
    0.89
    POSITIVE LOGITS
    st
    2.56
    ST
    1.90
    xbet
    1.89
    stArray
    1.68
    хбет
    1.63
    sts
    1.57
     st
    1.50
    stom
    1.48
    0
    1.45
    stol
    1.37
    Activations Density 0.878%

    No Known Activations