© 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. 83296
    Prev
    Next
    INDEX
    Explanations

    tripod and bipod supports

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

    This neuron fires on sequences of digits (often with hyphens), i.e. model numbers, patent numbers, years, or other technical numeric identifiers.

    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
    Trong
    -0.75
    ഓ
    -0.74
    smar
    -0.73
     Anat
    -0.72
    ӹ
    -0.71
    Fors
    -0.68
     quantities
    -0.67
    unächst
    -0.66
    Tan
    -0.66
     intram
    -0.66
    POSITIVE LOGITS
     tripod
    3.63
     Tripod
    2.56
    tri
    1.63
     tri
    1.54
     trí
    1.49
     stand
    1.38
     три
    1.38
    三
    1.38
    Tri
    1.30
     mount
    1.25
    Activations Density 0.018%

    No Known Activations