© 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. 98946
    Prev
    Next
    INDEX
    Explanations

    file or data

    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
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -3.48
     both
    -2.19
     all
    -2.05
    ).
    -2.02
     any
    -1.88
     it
    -1.87
    );
    -1.87
     or
    -1.85
     after
    -1.82
     one
    -1.80
    POSITIVE LOGITS
    0
    2.09
     În
    1.80
     salari
    1.77
    k
    1.77
     mauva
    1.74
    桖
    1.73
    ⏑
    1.73
    queles
    1.72
    ientras
    1.71
    ING
    1.68
    Activations Density 0.214%

    No Known Activations