© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93529
    Prev
    Next
    INDEX
    Explanations

    version numbers and specific actions

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

    This neuron detects numeric sequences (e.g. version numbers, page numbers, counts) 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
     לד
    -0.64
    »?
    -0.62
     nodes
    -0.61
     dentistry
    -0.61
    说话
    -0.61
     restricted
    -0.60
     Cassidy
    -0.59
    ochrome
    -0.59
     commuter
    -0.59
     현
    -0.58
    POSITIVE LOGITS
    欧
    0.76
    inario
    0.75
     stratos
    0.68
    개
    0.65
    erçe
    0.64
     Severity
    0.63
    攣
    0.63
    тай
    0.63
     Fg
    0.63
    Ẳ
    0.63
    Activations Density 0.046%

    No Known Activations