© 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. 113663
    Prev
    Next
    INDEX
    Explanations

    business services and institutions

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

    The main thing this neuron does is detect numeric tokens (e.g. standalone numbers, numeric sequences, and numeric values with decimals).

    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
    -2.02
    ?
    -1.88
    ”.
    -1.57
    aneity
    -1.55
    ,”
    -1.55
    ingly
    -1.48
    ();
    -1.45
    荭
    -1.45
    ».
    -1.45
    岨
    -1.44
    POSITIVE LOGITS
    impôt
    1.77
    zelfde
    1.76
    $--
    1.71
    évaluation
    1.56
    investissement
    1.55
     tiež
    1.52
     cũng
    1.51
     первая
    1.48
     вторая
    1.47
    élaboration
    1.45
    Activations Density 0.130%

    No Known Activations