© 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. 84466
    Prev
    Next
    INDEX
    Explanations

    assembly metadata

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

    The neuron detects numeric tokens (sequences of digits) 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
     zanah
    -0.76
    strftime
    -0.72
    Pé
    -0.71
     bequest
    -0.69
     направи
    -0.69
    ÁND
    -0.68
     cleans
    -0.66
    LETE
    -0.66
    sessions
    -0.65
    équences
    -0.64
    POSITIVE LOGITS
    mming
    0.78
     Baer
    0.78
     verdo
    0.75
    iis
    0.70
    domésticos
    0.70
     запи
    0.69
    ;</
    0.69
    valu
    0.68
     acht
    0.68
     사
    0.67
    Activations Density 0.077%

    No Known Activations