© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    file paths and names

    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
    <eos>
    1.33
    ↵↵
    1.19
     ;{
    1.10
     ;,
    1.08
    ↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵
    1.06
    :“
    1.06
    ↵↵↵↵↵
    1.04
    ：“
    1.03
     ※
    1.03
    POSITIVE LOGITS
    .
    1.30
    *.
    1.26
     ہوئی۔
    1.24
    _.
    1.11
     ہوئے۔
    1.08
    __.
    1.02
     ہوا۔
    0.99
    /*.
    0.99
    ++.
    0.98
     دی۔
    0.93
    Activations Density 0.091%

    No Known Activations