© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48848
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

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

    The neuron activates on numeric tokens (digits, numbers, and numeric symbols).

    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
     plages
    -0.81
    amię
    -0.79
     география
    -0.75
     nage
    -0.72
    ubu
    -0.71
    Service
    -0.69
    (){}
    -0.69
    assumed
    -0.69
    ++.
    -0.68
     ſu
    -0.68
    POSITIVE LOGITS
     voordeel
    0.78
    Scooby
    0.77
    Antal
    0.75
    imbawa
    0.75
     wheat
    0.75
    CustomerID
    0.75
     timbers
    0.74
    esez
    0.74
    skich
    0.73
     bros
    0.72
    Activations Density 0.028%

    No Known Activations