© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20020
    Prev
    Next
    INDEX
    Explanations

    same

    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
    )-
    -1.90
     legt
    -1.80
     unrivalled
    -1.78
     ........
    -1.76
    ྵ
    -1.73
     Ausland
    -1.70
    偁
    -1.70
    )...
    -1.68
    𐬹
    -1.68
    
    -1.66
    POSITIVE LOGITS
     because
    1.96
    just
    1.91
     before
    1.84
    because
    1.78
    節約
    1.73
     until
    1.66
     lainnya
    1.65
     only
    1.64
     for
    1.63
     when
    1.61
    Activations Density 0.030%

    No Known Activations