© 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. 127620
    Prev
    Next
    INDEX
    Explanations

    or and other options

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

    The neuron detects adverbs and phrases that specify alternate locations or mobility contexts (e.g. “away,” “at home,” “on the go”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     engel
    -1.84
    儅
    -1.77
     veren
    -1.76
     kredi
    -1.70
    isering
    -1.59
     spesifik
    -1.55
     rokok
    -1.55
    ledes
    -1.54
     ſy
    -1.54
     tabak
    -1.53
    POSITIVE LOGITS
     These
    1.96
     our
    1.80
     Our
    1.77
    drawSprites
    1.71
     Those
    1.66
     other
    1.66
     When
    1.63
     Когда
    1.60
     the
    1.59
     unsere
    1.59
    Activations Density 0.144%

    No Known Activations