© 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. 1188
    Prev
    Next
    INDEX
    Explanations

    shell commands

    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
    에
    3.08
    o
    2.88
    ̳
    2.71
    a
    2.66
    enzen
    2.47
    in
    2.30
    場合に
    2.29
    on
    2.26
    გუფი
    2.22
    ᆯ
    2.22
    POSITIVE LOGITS
    ﮄ
    2.92
    lerde
    2.76
    larla
    2.76
    leri
    2.64
    larını
    2.58
    ları
    2.57
    larından
    2.57
    larının
    2.47
    larına
    2.46
    えられる
    2.41
    Activations Density 0.789%

    No Known Activations