© 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. 13979
    Prev
    Next
    INDEX
    Explanations

    coding snake games

    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
    det
    2.61
    jsp
    2.51
    %@",
    2.39
     det
    2.36
    𝒅
    2.30
    dv
    2.26
    kład
    2.25
     نحل
    2.23
    ct
    2.20
    PG
    2.20
    POSITIVE LOGITS
    𝑠
    2.96
    𝑒
    2.89
    𝑖
    2.85
    𝑦
    2.77
    тік
    2.69
    स
    2.56
    𝑚
    2.49
    𝑧
    2.46
    𝑢
    2.45
    чика
    2.42
    Activations Density 0.017%

    No Known Activations