© 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. 34-GEMMASCOPE-RES-131K
    7. 3167
    Prev
    Next
    INDEX
    Explanations

    Eifficient Limits Field

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

    The neuron strongly activates on isolated numeric characters (digits) 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_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
    ன்ற
    -0.85
     краще
    -0.77
    ennan
    -0.75
    IENT
    -0.75
     apenas
    -0.74
     OnDestroy
    -0.73
     працю
    -0.73
    valho
    -0.73
     zobac
    -0.73
    占比
    -0.73
    POSITIVE LOGITS
    ght
    0.88
     libraries
    0.85
    DBConnection
    0.84
    ри
    0.79
     жителей
    0.78
     díl
    0.77
     dining
    0.77
     violation
    0.77
    ="${
    0.76
     trinken
    0.75
    Activations Density 0.062%

    No Known Activations