© 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. 62467
    Prev
    Next
    INDEX
    Explanations

    enabled or true values

    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
    ComponentScan
    -0.86
    icolon
    -0.83
     particular
    -0.82
    銜
    -0.82
    F
    -0.81
     such
    -0.79
    Ostat
    -0.79
    Podob
    -0.78
     puzzling
    -0.77
     peculiarity
    -0.77
    POSITIVE LOGITS
     yes
    2.47
    yes
    2.13
     YES
    1.88
     Yes
    1.80
    Yes
    1.71
    YES
    1.69
     true
    1.62
     sì
    1.53
     sí
    1.30
    TRUE
    1.27
    Activations Density 0.092%

    No Known Activations