© 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. 47209
    Prev
    Next
    INDEX
    Explanations

    degree severity extent magnitude

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Stimmung
    -0.80
    LLVM
    -0.77
     Academies
    -0.77
     constamment
    -0.77
    ギュ
    -0.75
     reconocida
    -0.75
     Boogie
    -0.74
     sûrement
    -0.73
     constantemente
    -0.73
     confusion
    -0.73
    POSITIVE LOGITS
     extent
    5.16
     degree
    4.84
    extent
    3.92
     magnitude
    3.77
    degree
    3.72
     severity
    3.50
    程度
    3.41
     Extent
    3.41
    Extent
    3.39
     Degree
    3.27
    Activations Density 0.321%

    No Known Activations