© 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. 73104
    Prev
    Next
    INDEX
    Explanations

    identity statements

    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
     agujero
    -2.03
     neumáticos
    -1.77
    鲩
    -1.69
    Doesn
    -1.68
    www
    -1.67
    なども
    -1.65
     rých
    -1.62
     mettant
    -1.61
    把自己
    -1.59
     abbildung
    -1.58
    POSITIVE LOGITS
     Many
    1.66
     “(
    1.59
     Often
    1.59
     Perhaps
    1.57
     Although
    1.50
     one
    1.48
     Quite
    1.48
     Though
    1.48
    </sup>
    1.45
     spurred
    1.45
    Activations Density 0.038%

    No Known Activations