© 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. 106129
    Prev
    Next
    INDEX
    Explanations

    HTML element start tags

    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
     that
    -1.90
     However
    -1.57
    Föld
    -1.55
    Elő
    -1.52
     their
    -1.48
    Both
    -1.45
    Those
    -1.45
    Despite
    -1.44
     from
    -1.42
    With
    -1.41
    POSITIVE LOGITS
    <
    1.98
    なので
    1.42
     <
    1.36
    ковая
    1.35
    if
    1.34
    があり
    1.30
     wondrous
    1.24
    ínu
    1.20
     marvelous
    1.16
     quintessential
    1.15
    Activations Density 0.030%

    No Known Activations