© 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. 16392
    Prev
    Next
    INDEX
    Explanations

    definite article followed by nouns

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

    The neuron activates on numeric literals (sequences of digits) in code.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ichert
    -1.63
    Thema
    -1.59
    bsen
    -1.57
    𖧵
    -1.57
    Took
    -1.55
    mme
    -1.53
    𖣔
    -1.52
    
    -1.51
     borbo
    -1.50
     ferocious
    -1.48
    POSITIVE LOGITS
     from
    2.00
     specified
    1.57
     system
    1.55
     provided
    1.52
    It
    1.46
     every
    1.42
     already
    1.42
     regularly
    1.40
     by
    1.40
     with
    1.40
    Activations Density 0.157%

    No Known Activations