© 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. 32575
    Prev
    Next
    INDEX
    Explanations

    characteristic followed by descriptor

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

    The neuron specifically detects occurrences of the word “characteristic” in technical or scientific contexts.

    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
    ."
    -2.86
     icône
    -2.63
    嫫
    -2.58
    栊
    -2.53
     activité
    -2.36
    derdag
    -2.34
    ଢ
    -2.16
    тория
    -2.14
    龉
    -2.14
     или
    -2.13
    POSITIVE LOGITS
    0
    2.66
     ‘‘
    2.44
     “
    2.34
    それにしても
    2.28
    нимание
    2.23
    стреча
    2.22
    ul
    2.16
    ,’
    2.13
    ’,
    2.13
    ation
    2.13
    Activations Density 0.033%

    No Known Activations