© 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. 32823
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

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

    The neuron fires on standalone numeric tokens (multi‐digit numbers) in structured 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     måneder
    -1.32
     podoba
    -1.20
     hombro
    -1.16
     nová
    -1.10
    nze
    -1.10
    瘘
    -1.09
    をつけ
    -1.08
    beak
    -1.08
    mopolitan
    -1.06
     vänner
    -1.06
    POSITIVE LOGITS
     even
    1.13
    P
    1.09
    have
    1.06
    A
    1.00
    O
    0.99
     others
    0.99
    J
    0.97
     "
    0.96
    even
    0.96
    ´
    0.95
    Activations Density 0.009%

    No Known Activations