© 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. 73119
    Prev
    Next
    INDEX
    Explanations

    sections, articles, chapters, papers

    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
     this
    -2.05
     sehr
    -1.80
     diferentes
    -1.67
     very
    -1.63
     not
    -1.61
     two
    -1.60
     our
    -1.60
     by
    -1.55
     unique
    -1.54
     different
    -1.53
    POSITIVE LOGITS
     Eſ
    2.30
     Theſe
    1.99
     $_=
    1.91
    蝼
    1.89
     triomphe
    1.87
     chré
    1.85
     ſer
    1.84
     chrétien
    1.82
     boute
    1.78
    アプリケーション
    1.77
    Activations Density 0.638%

    No Known Activations