© 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. 128466
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron fires on numeric literals (especially those with decimals) in equations or code.

    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
    鸸
    -1.49
     ་
    -1.38
    OVERN
    -1.35
    giày
    -1.34
    ίας
    -1.32
     Turbul
    -1.29
     behaupten
    -1.26
    罴
    -1.23
     occuper
    -1.23
     соответствует
    -1.23
    POSITIVE LOGITS
     will
    1.83
     —
    1.30
     or
    1.24
    胧
    1.24
     --
    1.22
     zobaczyć
    1.20
    __(
    1.20
    :'#
    1.20
     khác
    1.19
    haviours
    1.17
    Activations Density 0.011%

    No Known Activations