© 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. 127813
    Prev
    Next
    INDEX
    Explanations

    max

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

    The neuron strongly activates on numeric literals (integers or decimals) 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
     löyty
    -1.70
    ギュア
    -1.69
     många
    -1.69
     färg
    -1.63
     résister
    -1.63
     olika
    -1.63
    飆
    -1.63
     polaire
    -1.60
     dépenses
    -1.58
     blessure
    -1.56
    POSITIVE LOGITS
    :
    2.02
     using
    1.91
     one
    1.80
     anything
    1.73
     what
    1.67
     giving
    1.67
     such
    1.66
     can
    1.59
     so
    1.57
     each
    1.54
    Activations Density 0.025%

    No Known Activations