© 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. 50493
    Prev
    Next
    INDEX
    Explanations

    HTML declarations and links

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

    The neuron activates on standalone numeric tokens—i.e. sequences of digits (especially multi-digit integers).

    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
     pieza
    -0.84
     narci
    -0.84
    damp
    -0.84
     עבודה
    -0.79
    Mappings
    -0.77
    Przy
    -0.75
     ocasião
    -0.75
    levelse
    -0.75
     implantation
    -0.74
    Enviado
    -0.74
    POSITIVE LOGITS
     elements
    0.90
    ucleotide
    0.83
    argli
    0.82
     nhu
    0.81
    penes
    0.80
     Todd
    0.77
    Operator
    0.75
    ovina
    0.74
     Two
    0.74
     zupełnie
    0.73
    Activations Density 0.002%

    No Known Activations