© 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. 85359
    Prev
    Next
    INDEX
    Explanations

    code structure and variable names

    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
     or
    -1.86
     your
    -1.71
     that
    -1.70
    他們
    -1.70
     они
    -1.54
    </em>
    -1.52
    </i>
    -1.50
    as
    -1.49
     You
    -1.47
     please
    -1.45
    POSITIVE LOGITS
     camion
    1.72
     tragedia
    1.70
     misterioso
    1.66
     cromo
    1.65
     coton
    1.62
     idiota
    1.61
     tortura
    1.56
     monstru
    1.53
     tableta
    1.53
     milliards
    1.52
    Activations Density 0.001%

    No Known Activations