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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60707
    Prev
    Next
    INDEX
    Explanations

    Schwartz, Kuhn, Russo, KR, DBA

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on uppercase names and acronyms—that is, multi‐letter all‐caps tokens denoting people, organizations, or technical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    籏
    -3.00
    薷
    -2.95
    ⏑
    -2.88
    
    -2.59
    i
    -2.59
    蕻
    -2.58
    鉏
    -2.53
    푆
    -2.53
    s
    -2.52
    
    -2.52
    POSITIVE LOGITS
    '
    4.13
     "
    2.95
    *
    2.69
    [
    2.66
    -
    2.64
     große
    2.56
    {
    2.55
    -"
    2.44
    ."
    2.33
    .'
    2.31
    Activations Density 0.021%

    No Known Activations