© 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. 128032
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    lists of elements or code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    為に
    -1.70
     "
    -1.63
     even
    -1.62
     different
    -1.54
     will
    -1.47
    様な
    -1.33
    にします
    -1.32
     either
    -1.31
    ようです
    -1.31
    際に
    -1.30
    POSITIVE LOGITS
    などが
    1.77
    などを
    1.62
    などは
    1.62
     faciliter
    1.62
    そして
    1.61
    もあって
    1.48
    なども
    1.46
    があり
    1.44
     diriger
    1.38
    も多く
    1.38
    Activations Density 0.037%

    No Known Activations