© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67390
    Prev
    Next
    INDEX
    Explanations

    exclamations and short phrases

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

    This neuron fires on short exclamatory or interjection utterances in dialogue (e.g. “Oh,” “What’s,” “No,” “Spike!”).

    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
     präsenti
    -1.54
    茳
    -1.45
     auß
    -1.44
    )
    -1.41
     Schluß
    -1.34
     pegatinas
    -1.34
     that
    -1.33
     enthou
    -1.30
     hırka
    -1.30
     Agustus
    -1.30
    POSITIVE LOGITS
     of
    1.73
     there
    1.48
     by
    1.48
     so
    1.44
    zkiem
    1.39
     have
    1.38
     we
    1.32
    ViewChild
    1.28
    zenz
    1.28
     if
    1.28
    Activations Density 0.010%

    No Known Activations