© 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. 109421
    Prev
    Next
    INDEX
    Explanations

    wheel bolt pattern specifications

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

    The neuron activates on numeric tokens—especially digits and measurement specifications (e.g. wheel dimensions).

    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
    penn
    -0.79
    Segment
    -0.73
    ȝ
    -0.71
    Entertainment
    -0.71
    maxLines
    -0.70
    ⌋
    -0.69
    entertainment
    -0.68
    Forms
    -0.68
     タイヤ
    -0.68
     entière
    -0.67
    POSITIVE LOGITS
     bolt
    1.70
     pattern
    1.39
    Holes
    1.32
     PCD
    1.30
     Bolt
    1.28
    Bolt
    1.26
    bolt
    1.23
    pattern
    1.20
     Pattern
    1.17
    PCD
    1.17
    Activations Density 0.022%

    No Known Activations