© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13570
    Prev
    Next
    INDEX
    Explanations

    surrealist and surrealism

    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
    r
    4.05
    u
    3.47
    ر
    3.13
    rn
    3.12
    rige
    3.11
    rne
    3.10
    ن
    3.07
    rary
    3.05
    uose
    2.97
    ಾ
    2.94
    POSITIVE LOGITS
    ਂ
    2.99
    $[
    2.90
    $\
    2.88
    ਣੀ
    2.61
    μφ
    2.57
    getFirst
    2.52
    Lo
    2.47
    Giá
    2.47
    备
    2.43
    gee
    2.40
    Activations Density 0.022%

    No Known Activations