© 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. 1812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <unused1171>
    1.95
    <unused172>
    1.87
    <unused68>
    1.86
    <unused1229>
    1.86
    <unused119>
    1.85
    <unused21>
    1.85
    <unused1621>
    1.84
    gheatmap
    1.83
    <unused958>
    1.82
    <unused120>
    1.82
    POSITIVE LOGITS
    <b>
    1.07
    ↵↵
    1.07
    //
    1.03
    ↵
    1.03
    <i>
    1.02
    </i>
    0.97
    ...
    0.96
    ↵↵↵
    0.96
     //
    0.95
      
    0.91
    Activations Density 3.247%

    No Known Activations