© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1663
    Prev
    Next
    INDEX
    Explanations

    Alliance Against, Kamala Harris, Van der Kolk

    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_65k_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
     cov
    0.93
     namin
    0.87
     verhind
    0.85
     proguardFiles
    0.84
    <unused298>
    0.83
     purely
    0.81
     adjourn
    0.79
     unbe
    0.79
     drooping
    0.77
     trailing
    0.76
    POSITIVE LOGITS
     eds
    1.29
    .).
    1.28
    .,
    1.21
     Institute
    1.14
     et
    1.13
    .(
    1.11
     ibid
    1.10
    .].
    1.09
    ,【
    1.08
     Handbook
    1.07
    Activations Density 1.011%

    No Known Activations