© 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. 98771
    Prev
    Next
    INDEX
    Explanations

    describing composites

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

    The neuron activates whenever it encounters the word “composite,” regardless of context.

    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
    ⩴
    -2.41
     jejich
    -2.34
     stück
    -2.31
    ῞
    -2.31
    .
    -2.25
     obsahuje
    -2.20
    颏
    -2.17
     pracov
    -2.13
     informace
    -2.06
     pôr
    -2.06
    POSITIVE LOGITS
     While
    2.69
     Also
    2.67
     From
    2.63
     Like
    2.58
     Does
    2.58
    [
    2.33
    呖
    2.27
    </strong>
    2.22
    晅
    2.19
    ↵
    2.13
    Activations Density 0.009%

    No Known Activations