© 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. 100080
    Prev
    Next
    INDEX
    Explanations

    sports news and results

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

    This neuron activates on tokens that are numeric expressions—scores, statistics, measurements, or other numbers (including decimals and percentages).

    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
     if
    -1.45
     katun
    -1.45
     comodidades
    -1.41
     réfrig
    -1.40
     dekoratif
    -1.37
     Notwendigkeit
    -1.34
     patata
    -1.33
     carburant
    -1.30
     manquer
    -1.30
     demandent
    -1.29
    POSITIVE LOGITS
     out
    1.51
     четырех
    1.48
     at
    1.38
     S
    1.38
     cuyos
    1.34
    摒
    1.34
     with
    1.33
    L
    1.30
     s
    1.27
    D
    1.27
    Activations Density 0.037%

    No Known Activations