© 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. 10-GEMMASCOPE-RES-131K
    7. 6977
    Prev
    Next
    INDEX
    Explanations

    synthesized equation

    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_10/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
     even
    -2.09
     their
    -1.99
     only
    -1.95
     which
    -1.84
     its
    -1.77
     where
    -1.67
     that
    -1.63
     may
    -1.58
     also
    -1.53
     irrespective
    -1.52
    POSITIVE LOGITS
     niem
    1.73
    kanak
    1.66
    blins
    1.63
    媗
    1.63
    ’
    1.62
    tinggi
    1.56
    
    1.53
    }>;
    1.53
    scaleY
    1.51
    lâ
    1.50
    Activations Density 0.257%

    No Known Activations