© 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. 16648
    Prev
    Next
    INDEX
    Explanations

    technical terms and prepositions

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

    The neuron fires on tokens that appear in technical specifications or dimensional contexts—numbers, measurement terms, version/step identifiers, and similar specification language.

    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
    Irlande
    -1.41
    ᾽
    -1.40
     ложка
    -1.38
    eses
    -1.37
    rechten
    -1.37
     бампер
    -1.35
     berbagai
    -1.30
     Dingen
    -1.30
    Égypte
    -1.30
    eding
    -1.28
    POSITIVE LOGITS
     your
    1.37
     државе
    1.27
     beeintr
    1.20
     you
    1.19
     alemania
    1.16
     zostanie
    1.15
    វ
    1.14
    药
    1.14
     Ucraina
    1.13
    要
    1.13
    Activations Density 0.065%

    No Known Activations