© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    years and numbers

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

    The neuron is tuned to pick out numeric measurements (especially decimal or floating-point numbers) 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
     ingresso
    -1.78
     sedu
    -1.67
     inverno
    -1.65
    閖
    -1.59
    particularly
    -1.55
     vitu
    -1.55
     levering
    -1.55
     indisponible
    -1.54
     ainfi
    -1.54
     extingu
    -1.50
    POSITIVE LOGITS
     no
    1.85
     —
    1.57
     but
    1.52
     tipo
    1.48
     -
    1.45
    s
    1.45
     и
    1.42
     and
    1.41
     because
    1.38
     If
    1.38
    Activations Density 0.001%

    No Known Activations