© 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. 47057
    Prev
    Next
    INDEX
    Explanations

    Every once, Two confirmed

    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
     most
    -0.84
    嶌
    -0.79
    lais
    -0.78
     veel
    -0.77
    Điều
    -0.76
    Employers
    -0.76
    geslacht
    -0.76
     épic
    -0.76
     nombreux
    -0.75
     jedem
    -0.75
    POSITIVE LOGITS
    inline
    1.05
    requires
    0.93
    íny
    0.86
     genuine
    0.85
     mView
    0.82
     famí
    0.81
    Ӝ
    0.80
    resas
    0.79
     requires
    0.79
     messe
    0.78
    Activations Density 0.021%

    No Known Activations