© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11664
    Prev
    Next
    INDEX
    Explanations

    action or description of sequences

    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_13_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
    น
    1.27
    นิยม
    1.18
    Nearby
    1.14
    a
    1.13
    屋
    1.10
    ्
    1.09
    ر
    1.08
    ायला
    1.07
    i
    1.07
    にい
    1.05
    POSITIVE LOGITS
    detailID
    1.39
     cuộc
    1.34
     adolescentes
    1.33
    studentRecord
    1.33
     Emiliano
    1.32
     Margot
    1.32
     еже
    1.31
    <unused1210>
    1.30
    userDetail
    1.30
    <unused2137>
    1.29
    Activations Density 0.000%

    No Known Activations