© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31630
    Prev
    Next
    INDEX
    Explanations

    programming or abbreviations

    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
     so
    -0.98
     przecież
    -0.89
     undoubtedly
    -0.83
     nearly
    -0.82
     keperluan
    -0.80
     remarkable
    -0.79
     unparalleled
    -0.78
     arguably
    -0.77
     ((
    -0.76
     usually
    -0.75
    POSITIVE LOGITS
    תיים
    0.93
    utro
    0.93
     expected
    0.92
    /
    0.90
     proclaims
    0.90
     expectations
    0.90
     provar
    0.90
     comentários
    0.86
    PerformLayout
    0.86
    ύν
    0.86
    Activations Density 0.006%

    No Known Activations