© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67748
    Prev
    Next
    INDEX
    Explanations

    dates and publications

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

    The neuron fires on capitalized named‐entity tokens—proper names of organizations, publications, dates, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     flotte
    -0.98
     weren
    -0.96
    Loire
    -0.95
     варіан
    -0.94
    嫵
    -0.94
    aggia
    -0.93
    Hilsen
    -0.92
     отличие
    -0.91
    tagext
    -0.90
    ificaciones
    -0.89
    POSITIVE LOGITS
     that
    2.06
     which
    1.62
     about
    1.32
     involving
    1.29
     where
    1.09
     που
    1.06
     wherein
    1.03
     которое
    1.03
     Yes
    1.02
     of
    1.01
    Activations Density 0.092%

    No Known Activations