© 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. 22-GEMMASCOPE-RES-131K
    7. 127846
    Prev
    Next
    INDEX
    Explanations

    {% if %}, begin, Erinnyis, Barbecue, United

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     this
    -1.58
     one
    -1.47
     and
    -1.32
     terraza
    -1.25
     all
    -1.23
     what
    -1.22
     only
    -1.19
     which
    -1.14
     more
    -1.14
     as
    -1.13
    POSITIVE LOGITS
     ayur
    1.32
     Atención
    1.30
    MUST
    1.30
    少し
    1.22
    does
    1.21
     ∆
    1.20
    during
    1.20
     goofy
    1.20
     Dinas
    1.18
     stratigraph
    1.17
    Activations Density 0.004%

    No Known Activations