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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104916
    Prev
    Next
    INDEX
    Explanations

    Spartans, imbalance, chapters

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

    This neuron detects tokens that serve as section or chapter headings—i.e. markers of document structure rather than running text.

    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
    栳
    -2.95
     fabulous
    -2.88
    臜
    -2.84
    
    -2.77
     myriad
    -2.75
     decidedly
    -2.75
     essas
    -2.73
     mehrere
    -2.73
    縢
    -2.73
    llavero
    -2.53
    POSITIVE LOGITS
    e
    2.44
    X
    2.19
    蹋
    2.17
    鸯
    2.14
    C
    2.13
    I
    2.13
    and
    2.11
    CHREIB
    2.11
     給
    2.08
    屄
    2.06
    Activations Density 0.005%

    No Known Activations