© 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. 128996
    Prev
    Next
    INDEX
    Explanations

    number of actions

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

    The neuron activates on numeric expressions (digits or numbers) in the 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
     lorsque
    -1.35
     already
    -1.32
     twa
    -1.27
     eventuali
    -1.16
     lorsqu
    -1.14
    ‰
    -1.13
     本店
    -1.13
     месте
    -1.12
     tien
    -1.12
     quando
    -1.11
    POSITIVE LOGITS
     over
    1.28
    次数
    1.21
     Opportunities
    1.16
     hikes
    1.16
     vezes
    1.15
    ()%
    1.13
    Schule
    1.13
    !="")
    1.13
    Selain
    1.13
    Sebelum
    1.13
    Activations Density 0.152%

    No Known Activations