© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103387
    Prev
    Next
    INDEX
    Explanations

    Z- prefix words

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

    The neuron activates on tokens containing digits, i.e. numerical strings.

    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
     аллер
    -0.88
     */;
    -0.81
    larıyla
    -0.78
     katika
    -0.76
    valdi
    -0.76
     okazji
    -0.75
    '(
    -0.74
    THISDAY
    -0.74
     different
    -0.73
     fazla
    -0.73
    POSITIVE LOGITS
     workday
    0.88
    anderen
    0.84
     Зо
    0.83
    üglich
    0.83
     alleg
    0.81
    IntArray
    0.80
     Zon
    0.76
    ksom
    0.76
     prado
    0.75
    ❿
    0.75
    Activations Density 0.062%

    No Known Activations