© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    measures of specific concepts

    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
    gyz
    2.12
    匐
    1.99
    僭
    1.89
    ylsulfanyl
    1.88
    󠁧
    1.88
    subfigure
    1.84
    ugoslav
    1.83
    ≔
    1.83
    enic
    1.82
    MeOH
    1.81
    POSITIVE LOGITS
     Today
    1.31
     can
    1.31
     (
    1.29
     ACE
    1.25
     feelings
    1.24
     will
    1.22
    ,
    1.22
     [
    1.21
     in
    1.19
    Today
    1.19
    Activations Density 0.112%

    No Known Activations