© 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. 72337
    Prev
    Next
    INDEX
    Explanations

    verified status

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

    The neuron detects occurrences of the word “Verified.”

    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
    blurRadius
    -2.27
    了过去
    -2.22
    ні
    -2.17
     cuyas
    -2.17
     we
    -2.17
     cuyos
    -2.16
     éstos
    -2.14
    ✇
    -2.14
     pokud
    -2.14
     omdat
    -2.14
    POSITIVE LOGITS
    .
    2.70
    Our
    2.67
    Even
    2.66
     palsu
    2.66
    There
    2.63
    Everything
    2.63
    Nearly
    2.56
    While
    2.55
    Many
    2.53
    Its
    2.52
    Activations Density 0.004%

    No Known Activations