© 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. 56656
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     потребу
    -0.69
    するのは
    -0.69
    distr
    -0.67
    孪
    -0.66
    ९
    -0.66
     powiet
    -0.65
     fifteen
    -0.65
    建て
    -0.65
    ⌒
    -0.64
     kien
    -0.64
    POSITIVE LOGITS
    inline
    0.95
    INLINE
    0.83
    koľvek
    0.79
     width
    0.78
    ੨
    0.78
    caption
    0.77
     canales
    0.77
     lymph
    0.77
     layoffs
    0.77
     OGSÅ
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.