© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12272
    Prev
    Next
    INDEX
    Explanations

    Global Goals Institute

    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
    ">⁡</
    3.31
    (/[
    3.22
     trialComponents
    3.16
    🖔
    3.01
     chercher
    2.99
     toolPath
    2.97
    𒅆
    2.93
    <unused790>
    2.93
    𒀊
    2.88
    <unused785>
    2.88
    POSITIVE LOGITS
    as
    2.48
    o
    2.46
    سى
    2.41
    got
    2.40
    ्स
    2.39
    en
    2.37
    on
    2.36
    س
    2.33
    ie
    2.32
    d
    2.28
    Activations Density 0.015%

    No Known Activations