© 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. 103278
    Prev
    Next
    INDEX
    Explanations

    referencing prior documents or statements

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

    The neuron highlights formal scholarly markers—tokens used to signal cross-references or taxonomic/classification headings in academic texts.

    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
     where
    -2.28
     as
    -1.95
     because
    -1.94
     which
    -1.78
     just
    -1.75
    だか
    -1.67
     only
    -1.66
     when
    -1.59
     especially
    -1.55
     through
    -1.53
    POSITIVE LOGITS
    ᓚ
    1.71
    
    1.66
     zoude
    1.55
    𓆏
    1.53
     travailler
    1.49
     tarta
    1.42
     bezw
    1.41
    씰
    1.40
     nî
    1.35
     constater
    1.34
    Activations Density 0.004%

    No Known Activations