© 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. 47853
    Prev
    Next
    INDEX
    Explanations

    as explanation or demonstration

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

    This neuron triggers on referential discourse cues that point the reader to accompanying visuals or examples (e.g. “as seen in the chart below,” “see”).

    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
     which
    -2.03
     марта
    -1.45
     now
    -1.41
     a
    -1.37
     stycznia
    -1.34
    劻
    -1.32
    ”、“
    -1.30
    isieren
    -1.30
    tisgarh
    -1.28
    ”,
    -1.27
    POSITIVE LOGITS
     ajoute
    1.75
     there
    1.73
     anteriormente
    1.56
    缡
    1.46
     originalmente
    1.46
     MAKING
    1.45
     wasn
    1.40
     fonctionne
    1.39
     prouve
    1.39
     previamente
    1.38
    Activations Density 0.027%

    No Known Activations