© 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. 10-GEMMASCOPE-RES-131K
    7. 127554
    Prev
    Next
    INDEX
    Explanations

    38th

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

    This neuron specifically detects the numeral “38” (i.e. the token “38”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     bytu
    -2.72
    瘊
    -2.66
     nové
    -2.63
     Entfer
    -2.41
    朦
    -2.38
    をしていた
    -2.36
     něm
    -2.34
    瑆
    -2.31
    鑷
    -2.31
    恣
    -2.31
    POSITIVE LOGITS
    m
    3.41
    X
    3.14
    a
    3.13
    ↵
    3.08
    h
    3.05
    n
    2.88
    N
    2.86
    2
    2.84
    in
    2.80
    l
    2.73
    Activations Density 0.017%

    No Known Activations