© 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. 22-GEMMASCOPE-RES-131K
    7. 73558
    Prev
    Next
    INDEX
    Explanations

    questions and specific terms

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

    The neuron activates on standalone numeric tokens (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_22/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
     was
    -1.71
     seem
    -1.62
     Einzelnen
    -1.54
     more
    -1.45
     their
    -1.38
     Augenblick
    -1.35
     Continues
    -1.34
     einige
    -1.32
     sebelum
    -1.30
     Would
    -1.29
    POSITIVE LOGITS
    ↵
    1.60
     fueran
    1.43
    Ꮸ
    1.41
    OUTUBE
    1.31
    uración
    1.29
    ↵↵
    1.29
     hubieran
    1.29
     HYDRO
    1.28
     студии
    1.28
    quisition
    1.27
    Activations Density 0.000%

    No Known Activations