© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72696
    Prev
    Next
    INDEX
    Explanations

    common nouns and entities

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

    This neuron fires on standalone identifiers or symbols—i.e. tokens that look like variable names (r′, y^), class‐style/CamelCase names (Horse, City), or other tech‐notation terms rather than ordinary words.

    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
     négoci
    -0.81
     scris
    -0.79
     violen
    -0.79
    Gente
    -0.78
    Calendario
    -0.77
    Articolo
    -0.76
    iencias
    -0.75
    Isolated
    -0.75
     portait
    -0.74
    Inhalts
    -0.73
    POSITIVE LOGITS
     Yak
    0.99
    所
    0.92
    ナの
    0.88
    горя
    0.82
     Leo
    0.80
    SqlParameter
    0.80
    OrEqualTo
    0.79
    kry
    0.79
     шах
    0.79
    投入
    0.78
    Activations Density 0.170%

    No Known Activations