© 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. 15188
    Prev
    Next
    INDEX
    Explanations

    了解详细介绍

    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
    -1.99
     or
    -1.74
     '';
    -1.63
    '';
    -1.57
     also
    -1.50
    !(:
    -1.49
     terwijl
    -1.36
     as
    -1.34
     while
    -1.34
     after
    -1.30
    POSITIVE LOGITS
     apont
    1.31
    0
    1.27
     菇
    1.25
    
    1.23
    瞟
    1.20
     gebunden
    1.20
     lança
    1.20
     Können
    1.20
    我們的
    1.19
     promove
    1.19
    Activations Density 0.008%

    No Known Activations