© 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. 83734
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    The neuron detects alphanumeric biomedical identifiers or codes (letter–digit sequences such as CD4, D+/R–, INaP, TRUDIL, etc.).

    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
     on
    -2.33
     as
    -2.08
     our
    -1.52
     although
    -1.51
     in
    -1.50
     ask
    -1.50
     Although
    -1.48
    !
    -1.48
     an
    -1.46
     like
    -1.46
    POSITIVE LOGITS
    itatea
    1.52
     باسلام
    1.38
     brillant
    1.38
     maniere
    1.37
     ſol
    1.37
     alli
    1.36
     lorsqu
    1.35
     perdre
    1.34
    strö
    1.34
    riy
    1.34
    Activations Density 0.387%

    No Known Activations