© 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. 73312
    Prev
    Next
    INDEX
    Explanations

    reports, product, guilty, wind, matter, degrees, event, hearing

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

    The neuron strongly activates on numeric tokens and technical numerical expressions (e.g. measurements, years, codes, section numbers).

    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
     you
    -1.96
     though
    -1.54
     all
    -1.50
     все
    -1.48
     aunque
    -1.39
     with
    -1.37
     even
    -1.34
     would
    -1.34
    "></
    -1.34
     on
    -1.31
    POSITIVE LOGITS
     ไม่มี
    1.62
     unicornio
    1.44
     same
    1.40
    saying
    1.34
    随后
    1.28
     immédiatement
    1.26
     elefante
    1.24
    WEBPACK
    1.24
     selben
    1.23
     cyclisme
    1.23
    Activations Density 0.114%

    No Known Activations