© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    sign extended

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

    The neuron is essentially detecting tokens that contain numeric characters (i.e. numbers or digits embedded in identifiers or literals).

    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
    gangssprach
    -0.84
     permettra
    -0.79
     Kanz
    -0.75
     whis
    -0.72
     メモ
    -0.71
     donnera
    -0.70
     sobra
    -0.69
     arries
    -0.69
     빠
    -0.69
     maravilh
    -0.69
    POSITIVE LOGITS
     extend
    1.72
     Extend
    1.69
    Extend
    1.68
    extend
    1.66
     extending
    1.60
     extends
    1.52
    extends
    1.38
     extended
    1.37
     extension
    1.34
    扩展
    1.32
    Activations Density 0.031%

    No Known Activations