© 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. 68493
    Prev
    Next
    INDEX
    Explanations

    how something works

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

    The neuron fires on occurrences of the word “function” (and its variants “functions”) in the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ſy
    -2.58
    湏
    -2.41
    憮
    -2.36
    鸸
    -2.34
    깽
    -2.17
    wakili
    -2.16
    Ꮵ
    -2.14
     simpto
    -2.13
    
    -2.11
    鶲
    -2.11
    POSITIVE LOGITS
    K
    3.02
    ”
    2.95
    on
    2.89
    (
    2.78
    ;
    2.67
    In
    2.58
    *
    2.55
    On
    2.52
     ,
    2.48
    …
    2.47
    Activations Density 0.033%

    No Known Activations