© 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. 21285
    Prev
    Next
    INDEX
    Explanations

    describes current state or time

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

    The neuron activates on numeric tokens—both integers and decimals—i.e. it spots numbers and measurements 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
     "
    -2.14
     —
    -1.83
     несмотря
    -1.72
     ",
    -1.71
     your
    -1.65
     mesma
    -1.63
     a
    -1.62
     девя
    -1.60
     will
    -1.57
     où
    -1.55
    POSITIVE LOGITS
     that
    2.25
    のが
    1.79
     they
    1.76
    umerable
    1.71
     gabbana
    1.54
    OREM
    1.52
     francisco
    1.52
     desactivar
    1.49
     этого
    1.46
    twas
    1.46
    Activations Density 0.011%

    No Known Activations