© 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. 32908
    Prev
    Next
    INDEX
    Explanations

    codes, currencies, items

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

    This neuron activates on numeric tokens (i.e. numbers or number‐like strings) in the text.

    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
     soit
    -0.96
     yere
    -0.96
     yoksa
    -0.93
    ésia
    -0.91
     laboral
    -0.91
    犍
    -0.89
    泻
    -0.88
    ꙮ
    -0.87
     surveillance
    -0.87
     rè
    -0.87
    POSITIVE LOGITS
     Böyle
    0.91
    เดียว
    0.81
    etration
    0.80
     Vorschlag
    0.79
     luogo
    0.78
     obdob
    0.76
    腩
    0.76
     various
    0.76
     Może
    0.76
    %，
    0.76
    Activations Density 0.054%

    No Known Activations