© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58200
    Prev
    Next
    INDEX
    Explanations

    in such a case

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

    The neuron fires on numeric tokens—especially floating‐point numbers and other number strings.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </td>
    -1.84
     такого
    -1.83
     таких
    -1.66
     takiego
    -1.55
     particolar
    -1.54
     virtù
    -1.52
     メモ
    -1.52
     przód
    -1.52
     Schluß
    -1.48
    —”
    -1.47
    POSITIVE LOGITS
     you
    1.82
     aventuras
    1.73
    งิน
    1.72
     mentiras
    1.66
     acceptez
    1.66
     a
    1.66
    -
    1.60
     criaturas
    1.59
     llorar
    1.58
     soñar
    1.57
    Activations Density 0.032%

    No Known Activations