© 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. 65379
    Prev
    Next
    INDEX
    Explanations

    technical and structured text

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

    The neuron selectively activates on single digits (numerals) embedded in text.

    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
     to
    -1.23
    텐
    -0.95
     despite
    -0.94
     as
    -0.93
     grafic
    -0.92
     urbano
    -0.90
     geral
    -0.89
     its
    -0.89
     aérea
    -0.88
    alamy
    -0.88
    POSITIVE LOGITS
    nade
    1.02
     dimming
    0.98
    这时
    0.98
    tells
    0.97
     principalement
    0.93
     anderes
    0.91
    hasta
    0.91
     عنوان
    0.90
    tried
    0.90
    anniversaire
    0.90
    Activations Density 0.000%

    No Known Activations