© 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. 45636
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron activates on sequences of digits (numeric tokens) in the text.

    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
     sportowe
    -2.45
    臜
    -2.33
     ulica
    -2.27
     salieron
    -2.22
     vélos
    -2.13
     stylu
    -2.11
    苌
    -2.09
     estábamos
    -2.08
     xícara
    -2.06
     navires
    -2.06
    POSITIVE LOGITS
    "
    2.33
    on
    2.31
    You
    2.28
     “
    2.17
    us
    2.13
    do
    2.08
    <
    2.08
    at
    2.03
     can
    1.95
    '
    1.95
    Activations Density 0.069%

    No Known Activations