© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    mathematical notation including absolute values

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     longstanding
    -2.53
     during
    -2.25
     bringing
    -2.22
    瑧
    -2.19
     markedly
    -2.19
    Donativos
    -2.16
     exquisitely
    -2.14
     psychotic
    -2.08
    هاء
    -2.08
     During
    -2.08
    POSITIVE LOGITS
     ridiculously
    3.09
     the
    2.97
     amazingly
    2.92
     insanely
    2.81
     incredibly
    2.81
    '
    2.69
     revamped
    2.59
     amazing
    2.55
     dreary
    2.53
     fantastic
    2.52
    Activations Density 0.002%

    No Known Activations