© 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. 34-GEMMASCOPE-RES-131K
    7. 47084
    Prev
    Next
    INDEX
    Explanations

    student nurses

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

    The neuron flags multi‐digit numeric tokens and alphanumeric codes—especially database accession numbers or identifiers.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     discontinuities
    -0.77
     Cơ
    -0.68
    mala
    -0.68
    Ǜ
    -0.66
    ORGANIZATION
    -0.66
     sewerage
    -0.66
     ổ
    -0.65
    raza
    -0.64
     recombinant
    -0.64
    妖精
    -0.63
    POSITIVE LOGITS
    meteor
    0.74
     Qual
    0.72
    ゴー
    0.69
     meteor
    0.68
     Stirling
    0.67
     APD
    0.67
     Simplemente
    0.65
    tfidf
    0.63
     Silurian
    0.63
     Concert
    0.63
    Activations Density 0.042%

    No Known Activations