© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19301
    Prev
    Next
    INDEX
    Explanations

    information K function

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

    The neuron selectively activates on mathematical notation and numeric expressions—especially variables with prime marks (e.g. g′, q′) and numbers in formulas or sequences.

    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
    wavering
    -1.34
    athetic
    -1.30
     durab
    -1.27
    relenting
    -1.24
    Сколько
    -1.16
    Люби
    -1.16
    şekkür
    -1.16
    🪸
    -1.16
     rossa
    -1.15
    acidade
    -1.14
    POSITIVE LOGITS
     between
    1.43
     \
    1.17
     not
    1.11
    *
    1.08
     northeastern
    1.07
    1.06
    考えた
    1.06
    ý
    1.05
     ""
    1.04
    なくても
    1.04
    Activations Density 0.044%
    No Known Activations