© 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. 59397
    Prev
    Next
    INDEX
    Explanations

    openapi, Mateo, MediaPlayer, Vivo, Algon, Bellas

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

    the neuron activates on numeric tokens, especially floating-point numbers.

    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
    at
    -3.41
    c
    -3.39
    </b>
    -3.17
    ());
    -3.06
    ka
    -2.86
    t
    -2.81
    le
    -2.80
    os
    -2.78
    {
    -2.73
    ");
    -2.67
    POSITIVE LOGITS
    pulseira
    2.88
     granja
    2.81
    臜
    2.80
    ⑊
    2.73
    廕
    2.67
     lakukan
    2.66
    湏
    2.58
     revés
    2.55
    祧
    2.48
     iglesia
    2.44
    Activations Density 0.164%

    No Known Activations