© 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. 10-GEMMASCOPE-RES-131K
    7. 39833
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by the

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

    The neuron detects numeric measurement values (especially decimal numbers) in technical or patent‐style 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_10/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
     by
    -2.61
    :
    -1.92
     it
    -1.69
     two
    -1.50
     three
    -1.46
     four
    -1.40
     using
    -1.38
     considerable
    -1.30
     five
    -1.23
     other
    -1.22
    POSITIVE LOGITS
     împreună
    1.29
     săptăm
    1.26
     decât
    1.26
     dlaczego
    1.24
     tôt
    1.23
     competición
    1.19
    hereinafter
    1.15
    ﺀ
    1.14
    konos
    1.14
     opérations
    1.14
    Activations Density 0.290%

    No Known Activations