© 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. 34-GEMMASCOPE-RES-131K
    7. 93389
    Prev
    Next
    INDEX
    Explanations

    buffet and meal service

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

    The neuron strongly activates on numeric tokens—especially times, quantities, and other digit-based expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    鹅
    -0.75
    jRadioButton
    -0.73
     замок
    -0.72
     frowns
    -0.70
    Pró
    -0.70
    FIGURES
    -0.69
    Hamlet
    -0.69
    Renato
    -0.69
    んで
    -0.69
    beam
    -0.67
    POSITIVE LOGITS
     buffet
    5.34
     buff
    4.09
    Buff
    4.00
     Buffet
    4.00
    buffet
    3.69
    buff
    3.63
     BUFF
    3.38
     Buff
    3.30
    BUFF
    3.06
     Buffett
    2.92
    Activations Density 0.033%

    No Known Activations