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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10988
    Prev
    Next
    INDEX
    Explanations

    Rust derive attributes

    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
    𝚊
    2.94
    𒂗
    2.86
    LevelLinking
    2.81
    serialize
    2.78
    emailer
    2.78
    <unused1617>
    2.73
    <unused1557>
    2.73
     İstifadə
    2.72
    Гра
    2.72
    <unused841>
    2.71
    POSITIVE LOGITS
    i
    4.25
    e
    4.14
    y
    3.63
    ي
    3.60
    ه
    3.52
    a
    3.43
    s
    3.21
    en
    3.14
    t
    3.03
    o
    2.77
    Activations Density 0.041%

    No Known Activations