© 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. 22-GEMMASCOPE-RES-131K
    7. 130070
    Prev
    Next
    INDEX
    Explanations

    This neuron detects formal research‐ or grant‐style language outlining roles, assignments, or methodological details.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    specify or differentiate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     before
    -1.04
     first
    -0.91
     zm
    -0.90
     on
    -0.89
     mostrado
    -0.88
    ciuto
    -0.86
     now
    -0.86
     this
    -0.86
     tudo
    -0.84
    ChangeEvent
    -0.84
    POSITIVE LOGITS
     specific
    2.42
     certain
    2.17
    Specific
    2.06
     particular
    2.05
    specific
    1.96
     different
    1.95
    特定
    1.85
     bestimmte
    1.76
    某个
    1.72
     poszczegól
    1.72
    Activations Density 0.162%

    No Known Activations