© 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. 30006
    Prev
    Next
    INDEX
    Explanations

    file/inode documentation

    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
     reportedly
    -0.96
    imensional
    -0.95
    lysninger
    -0.95
    [{\
    -0.93
    télé
    -0.93
    либо
    -0.90
     tæn
    -0.87
    Bigr
    -0.87
     валю
    -0.86
    ATEN
    -0.85
    POSITIVE LOGITS
    1.10
     its
    1.04
    了一個
    0.99
     这个
    0.98
    though
    0.97
    
    0.96
     arbeiten
    0.95
    绀
    0.92
    although
    0.91
    这个
    0.90
    Activations Density 0.020%

    No Known Activations