© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32785
    Prev
    Next
    INDEX
    Explanations

    holes and openings

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

    The neuron strongly activates on numeric tokens (e.g. measurements, counts, or other digit‐containing elements).

    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
    uploaded
    -0.75
    indiv
    -0.75
    去找
    -0.74
    ridges
    -0.74
    ;*
    -0.73
    шков
    -0.73
    teng
    -0.72
     desemple
    -0.69
     dà
    -0.68
    hosting
    -0.68
    POSITIVE LOGITS
     openings
    3.28
     hole
    3.16
     opening
    2.95
     holes
    2.91
     отверсти
    2.50
    hole
    2.44
    Hole
    2.42
     Hole
    2.38
     Holes
    2.25
    holes
    2.19
    Activations Density 0.132%

    No Known Activations