© 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. 99124
    Prev
    Next
    INDEX
    Explanations

    character limits

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

    The neuron is detecting numeric tokens (digit sequences and numbers).

    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
     filters
    -1.02
    filters
    -0.94
    setFilter
    -0.89
    Filters
    -0.87
     filter
    -0.86
     filtr
    -0.81
    Filter
    -0.80
     filtro
    -0.79
     Filters
    -0.78
     фильтр
    -0.77
    POSITIVE LOGITS
     limit
    1.59
     characters
    1.52
    limit
    1.48
     Limit
    1.44
    Limit
    1.44
     Limits
    1.34
     character
    1.30
     limited
    1.28
    limits
    1.27
    maxlength
    1.27
    Activations Density 0.021%

    No Known Activations