© 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. 127776
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric literals (integer tokens).

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

    function or method calls

    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
    u
    -1.27
    </em>
    -1.21
    g
    -1.16
    h
    -1.13
    na
    -1.12
    j
    -1.11
    v
    -1.09
    d
    -1.07
    K
    -1.04
    T
    -1.03
    POSITIVE LOGITS
    İş
    1.25
    Новый
    1.18
    erkek
    1.16
    eriam
    1.15
    Pilih
    1.09
    berikut
    1.09
     senderismo
    1.07
    pkins
    1.06
    Semua
    1.06
    kungan
    1.05
    Activations Density 0.002%

    No Known Activations