© 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. 30256
    Prev
    Next
    INDEX
    Explanations

    degrees, superscripts, and subscripts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ؛
    -0.86
     sejam
    -0.82
     ler
    -0.77
    都
    -0.77
     ।
    -0.75
    都没
    -0.73
     сразу
    -0.73
      
    -0.72
    如果您
    -0.72
     serem
    -0.72
    POSITIVE LOGITS
    CAPTION
    0.88
    čen
    0.84
    níci
    0.81
     aleación
    0.80
    Informe
    0.80
    (...)
    0.79
    Sade
    0.79
     側
    0.79
    羅斯
    0.77
    Eglise
    0.77
    Activations Density 0.191%

    No Known Activations