© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 440
    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_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
     (
    1.02
    ע
    0.75
     (!)
    0.74
    à
    0.73
     За
    0.72
    A
    0.72
     го
    0.71
    main
    0.69
    у
    0.69
     כל
    0.69
    POSITIVE LOGITS
    <unused2103>
    1.09
    <unused407>
    1.06
    <unused1230>
    1.06
    퍁
    1.06
    <unused397>
    1.06
    𒇫
    1.05
    <unused2071>
    1.04
     theseKeys
    1.04
    <unused576>
    1.03
    <unused410>
    1.03
    Activations Density 0.764%

    No Known Activations