© 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. 62638
    Prev
    Next
    INDEX
    Explanations

    way to / analysis of / measurement in / plans for

    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
    NOS
    -1.08
     regt
    -0.97
    $-$
    -0.96
     intorno
    -0.95
     écouter
    -0.94
    多年
    -0.93
    Radians
    -0.91
     erhielt
    -0.89
     sonor
    -0.88
    ߍ
    -0.86
    POSITIVE LOGITS
     in
    4.22
     within
    2.72
     inside
    2.47
     on
    2.27
     through
    2.05
     via
    2.03
     from
    1.95
     trong
    1.89
    ใน
    1.88
     using
    1.79
    Activations Density 0.462%

    No Known Activations