© 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. 22-GEMMASCOPE-RES-131K
    7. 130437
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on numeric data—especially measurements, counts, and other quantitative values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    by or through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    (!__
    -1.14
     neither
    -1.10
    
    -1.05
     chcete
    -1.02
     auseinander
    -1.02
     dì
    -0.99
     ゆう
    -0.98
    oque
    -0.95
     bạch
    -0.94
     rendimiento
    -0.93
    POSITIVE LOGITS
     by
    4.06
     through
    2.28
     because
    1.91
     pamamagitan
    1.91
     путем
    1.58
     poprzez
    1.57
     द्वारा
    1.52
     bằng
    1.52
     mediante
    1.51
     using
    1.41
    Activations Density 0.109%

    No Known Activations