© 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. 99037
    Prev
    Next
    INDEX
    Explanations

    2%

    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
    2
    -2.56
    8
    -1.96
    structing
    -1.81
    AN
    -1.79
     muchos
    -1.70
     puis
    -1.69
    或者
    -1.66
     oder
    -1.63
     ocho
    -1.62
     allora
    -1.59
    POSITIVE LOGITS
    acea
    2.13
    omores
    1.67
     sucedió
    1.67
    囵
    1.55
     quedará
    1.55
     eenvou
    1.54
            
    1.53
    ývá
    1.50
    encre
    1.50
    (%)
    1.48
    Activations Density 0.011%

    No Known Activations