© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1779
    Prev
    Next
    INDEX
    Explanations

    pain arc

    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_17_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
     Zhao
    1.40
    Zhao
    1.33
     Caval
    1.19
     Johnston
    1.17
     Marcin
    1.13
     Zhang
    1.13
     Karg
    1.13
     Ł
    1.11
     வால்
    1.11
     Wilcox
    1.10
    POSITIVE LOGITS
     Ref
    2.67
    Ref
    2.66
    REF
    2.62
    ref
    2.57
     REF
    2.53
    Refs
    2.39
     ref
    2.37
     Refs
    2.36
    refs
    2.23
     refs
    2.22
    Activations Density 0.911%

    No Known Activations