© 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. 8493
    Prev
    Next
    INDEX
    Explanations

    point in numerical contexts

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

    This neuron detects occurrences of the word “point” when it appears in numeric or measurement expressions (e.g. “three-point,” “11-point,” “two-point”).

    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
    0
    -2.36
    険
    -1.77
     abrió
    -1.70
     這
    -1.64
    1
    -1.63
     Número
    -1.55
     dopiero
    -1.54
    ずる
    -1.51
    boîte
    -1.48
     ganó
    -1.46
    POSITIVE LOGITS
     \
    2.19
    <bos>
    1.78
     \%$
    1.75
    ﮦ
    1.65
     bebes
    1.64
    ционер
    1.63
    ？）
    1.61
     ſever
    1.60
    苼
    1.58
     commotion
    1.55
    Activations Density 0.008%

    No Known Activations