© 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. 16760
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming bounds

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

    The neuron activates whenever the text contains the root “bound,” i.e. the words “bound” or “bounds.”

    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
    reathable
    -2.56
     agujeros
    -2.53
    渽
    -2.50
    .
    -2.33
     Temporary
    -2.28
     incendios
    -2.28
    咣
    -2.27
    gelegt
    -2.19
     salarios
    -2.16
     huellas
    -2.14
    POSITIVE LOGITS
    2
    3.20
    ers
    2.59
    9
    2.45
    *
    2.41
    ：《
    2.34
    ст
    2.31
    开始了
    2.28
    4
    2.25
     början
    2.23
    骉
    2.19
    Activations Density 0.011%

    No Known Activations