© 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. 50422
    Prev
    Next
    INDEX
    Explanations

    validation and methods

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

    The neuron is detecting numeric tokens (quantitative values or counts) 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_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
     retratos
    -0.81
     pourtant
    -0.80
     cálculos
    -0.80
    ాయ
    -0.79
     Boyd
    -0.77
    idir
    -0.77
     Calculations
    -0.76
     zdjęć
    -0.76
     Analyzed
    -0.75
     tevé
    -0.75
    POSITIVE LOGITS
     validation
    4.97
     Validation
    3.89
     validate
    3.78
    validation
    3.73
    Validation
    3.69
     validating
    3.55
     validated
    3.33
    validate
    3.16
     validations
    3.09
     Validate
    3.03
    Activations Density 0.218%

    No Known Activations