© 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. 22-GEMMASCOPE-2-RES-16K
    7. 44
    Prev
    Next
    INDEX
    Explanations

    Bruce Murphy, produces milk

    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_22_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>
    0.46
    ↵
    0.42
    ↵↵
    0.40
     complete
    0.39
      
    0.39
    [
    0.38
     l
    0.37
     sah
    0.36
    0.36
    \
    0.36
    POSITIVE LOGITS
    <unused477>
    0.64
    <unused453>
    0.63
    <unused353>
    0.62
    <unused610>
    0.61
    hattim
    0.58
    <unused357>
    0.58
    <unused1662>
    0.58
    agangan
    0.58
    <unused459>
    0.58
    <unused414>
    0.58
    Activations Density 4.881%

    No Known Activations