© 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. 114047
    Prev
    Next
    INDEX
    Explanations

    At the end of a context

    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
    Negative Logits
    <td>
    -2.00
    乚
    -1.98
    躥
    -1.96
    ");
    -1.93
    镡
    -1.90
    ="
    -1.88
    趿
    -1.87
    咘
    -1.87
    끽
    -1.87
    躂
    -1.84
    POSITIVE LOGITS
     because
    2.38
     if
    2.38
     when
    2.22
    and
    1.96
     at
    1.94
    ’
    1.93
     during
    1.91
    2
    1.89
     can
    1.84
    するので
    1.80
    Activations Density 0.090%

    No Known Activations