© 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. 32834
    Prev
    Next
    INDEX
    Explanations

    account, rights, date, future

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

    The neuron is primarily detecting numeric tokens—instances of numbers, dates, counts, or measurements within 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     солдат
    -1.33
     enorme
    -1.32
    )))))
    -1.24
    ;");
    -1.23
    خخ
    -1.23
    ⟹
    -1.18
    鋲
    -1.15
    ٥
    -1.10
     adic
    -1.09
     especial
    -1.09
    POSITIVE LOGITS
     your
    3.11
    your
    2.03
     you
    1.99
    Your
    1.80
     our
    1.70
    before
    1.49
     يمكنك
    1.48
     maail
    1.45
     votre
    1.41
     jää
    1.41
    Activations Density 0.106%

    No Known Activations