© 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. 15269
    Prev
    Next
    INDEX
    Explanations

    variable assignments and expressions

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

    The neuron fires on numeric literals (integer or decimal number tokens) in the 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
     Ubicación
    -1.16
     größe
    -1.03
     Accesorios
    -1.02
     Produtos
    -0.93
     Capacidad
    -0.91
     duración
    -0.89
     Estructura
    -0.88
     Mejora
    -0.88
     acontece
    -0.87
     ۱۴۰۰
    -0.87
    POSITIVE LOGITS
    CPtr
    0.89
     continuo
    0.88
    illants
    0.85
    ąć
    0.83
    ');?>
    0.82
    Donc
    0.82
    ərbaycan
    0.82
    Rp
    0.81
     Rp
    0.81
    риях
    0.81
    Activations Density 0.013%

    No Known Activations