© 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. 90203
    Prev
    Next
    INDEX
    Explanations

    Russian Orthodox

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

    The neuron specializes in detecting numerical tokens and sequences (e.g., digits, odds, measurements, and other quantities).

    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
    prägt
    -0.76
     Mose
    -0.74
    Segoe
    -0.70
    queryset
    -0.69
    ocats
    -0.68
    stoppable
    -0.68
     Bischof
    -0.67
    clerview
    -0.67
    やさ
    -0.67
    colormap
    -0.66
    POSITIVE LOGITS
     public
    0.86
     backers
    0.84
     payoff
    0.79
     popular
    0.77
    Supp
    0.76
     morning
    0.76
    랐
    0.75
    Sent
    0.75
    昌
    0.75
     Acres
    0.74
    Activations Density 0.011%

    No Known Activations