© 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. 100270
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron fires on numeric tokens or figures (e.g. standalone numbers, percentages, years) 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
     your
    -1.86
     these
    -1.61
     not
    -1.52
     you
    -1.49
    ciptakan
    -1.48
    ubakar
    -1.48
     our
    -1.43
    Etter
    -1.42
     вру
    -1.39
    According
    -1.37
    POSITIVE LOGITS
     "
    1.81
    ."
    1.58
    searching
    1.48
    "
    1.46
    utenants
    1.44
    Cordialement
    1.43
     spezi
    1.37
     ANTON
    1.36
     malla
    1.34
     maris
    1.34
    Activations Density 0.004%

    No Known Activations