© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73490
    Prev
    Next
    INDEX
    Explanations

    specific quotation marks

    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
    .
    -2.13
    _
    -2.06
     their
    -1.98
     new
    -1.97
     eight
    -1.92
    Those
    -1.88
     three
    -1.85
     that
    -1.85
    ;
    -1.80
     seven
    -1.77
    POSITIVE LOGITS
    ᵴ
    2.11
     două
    2.08
    rdoba
    1.92
    
    1.92
     timpul
    1.88
     echte
    1.87
     dà
    1.84
    !*\
    1.80
     soooo
    1.78
     perioada
    1.77
    Activations Density 0.000%

    No Known Activations