© 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. 127639
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (integer or decimal values).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    currency symbols and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     of
    -1.20
     the
    -1.12
     However
    -1.02
     Although
    -1.01
    (!__
    -0.99
     Because
    -0.98
     pondok
    -0.96
     He
    -0.94
     which
    -0.94
    Œuvres
    -0.91
    POSITIVE LOGITS
    thaf
    1.07
     немає
    1.05
     garantit
    1.02
     sachant
    1.00
     muere
    1.00
    ⑪
    0.99
     khoan
    0.98
     inclut
    0.97
    Création
    0.97
     모두
    0.97
    Activations Density 0.005%

    No Known Activations