© 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. 10-GEMMASCOPE-RES-131K
    7. 113368
    Prev
    Next
    INDEX
    Explanations

    snap

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

    The neuron strongly activates on any occurrence of the substring “snap” (in any case or form) in a token.

    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
     But
    -2.72
    媄
    -2.34
    瑄
    -2.34
     stihl
    -2.31
    鹚
    -2.25
     Comentarios
    -2.22
    俐
    -2.20
     Fotografía
    -2.17
     Artículos
    -2.17
     Início
    -2.17
    POSITIVE LOGITS
    e
    2.47
    灃
    2.31
     tierra
    2.11
    骘
    1.96
     svar
    1.95
     فرمان
    1.94
     grasa
    1.93
     inocente
    1.89
    Snap
    1.88
     caras
    1.88
    Activations Density 0.003%

    No Known Activations