© 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. 45580
    Prev
    Next
    INDEX
    Explanations

    code checks and assertions

    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
     leichten
    -2.36
    cences
    -2.02
     schnellen
    -1.99
     yine
    -1.91
     speziellen
    -1.91
     bedeckt
    -1.86
     kurzen
    -1.84
    M
    -1.83
     exuberant
    -1.81
     einfachen
    -1.80
    POSITIVE LOGITS
    1.99
    "},
    1.67
    </th>
    1.58
     russ
    1.53
     boh
    1.52
     wien
    1.52
    </h1>
    1.51
     Amerika
    1.48
     dhe
    1.48
     xxv
    1.48
    Activations Density 0.002%

    No Known Activations