© 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. 62719
    Prev
    Next
    INDEX
    Explanations

    numerical computation and methods

    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
     washes
    -0.82
    THISDAY
    -0.75
     khỏ
    -0.74
    振り返
    -0.69
     garlands
    -0.68
    mgmt
    -0.68
     gaga
    -0.66
     darted
    -0.66
     fades
    -0.66
    titan
    -0.65
    POSITIVE LOGITS
     numerical
    5.06
     Numerical
    4.19
    Numerical
    4.19
    numerical
    4.13
     numerically
    3.92
     numeric
    3.14
    数值
    2.97
     numer
    2.91
     Numer
    2.83
    numeric
    2.72
    Activations Density 0.115%

    No Known Activations