© 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. 58080
    Prev
    Next
    INDEX
    Explanations

    code assignments: variable to value

    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
     this
    -2.11
     our
    -1.88
     their
    -1.78
    </i>
    -1.75
    并将
    -1.60
    </u>
    -1.59
    According
    -1.57
    </b>
    -1.52
     the
    -1.44
     カップ
    -1.44
    POSITIVE LOGITS
    ⟣
    1.83
    ⎆
    1.79
     unending
    1.76
     spectacular
    1.73
     extremely
    1.73
    
    1.72
     exceptionally
    1.72
     ซึ่ง
    1.69
     eſſ
    1.68
     of
    1.64
    Activations Density 0.032%

    No Known Activations