© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38449
    Prev
    Next
    INDEX
    Explanations

    names and words like "ka", "Ee", "Mahi"

    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
    ၟ
    -2.13
    </em>
    -1.89
    ၞ
    -1.82
     that
    -1.78
    ');
    -1.77
    欷
    -1.77
     bidra
    -1.74
     länder
    -1.67
    ampiyon
    -1.66
    
    -1.63
    POSITIVE LOGITS
    despite
    2.02
    </h1>
    1.86
    self
    1.76
    usually
    1.75
    becomes
    1.67
    considering
    1.63
    represents
    1.63
    ften
    1.60
    perhaps
    1.58
    instead
    1.56
    Activations Density 0.011%

    No Known Activations