© 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. 73325
    Prev
    Next
    INDEX
    Explanations

    electrical specifications and datasheets

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

    The neuron consistently activates on multi‐digit numeric tokens, i.e. sequences of digits representing numerical values.

    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
     PRACTICES
    -0.75
     conceived
    -0.73
    무
    -0.69
    ┠
    -0.69
     socie
    -0.68
    ırs
    -0.68
    ರಿ
    -0.67
     causas
    -0.66
     THOUGH
    -0.66
    ãs
    -0.66
    POSITIVE LOGITS
     electrical
    1.18
    Electrical
    1.01
     absolute
    1.00
     Absolute
    0.96
     Electrical
    0.95
    Absolute
    0.92
     maximum
    0.91
     min
    0.90
     operating
    0.89
     limits
    0.85
    Activations Density 0.010%

    No Known Activations