© 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. 14551
    Prev
    Next
    INDEX
    Explanations

    South Asian 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
    z
    -2.91
    '
    -2.41
    O
    -2.16
    
    -1.89
    h
    -1.88
    q
    -1.88
    w
    -1.81
    m
    -1.77
    os
    -1.74
    也在
    -1.70
    POSITIVE LOGITS
    悧
    1.92
    ěte
    1.92
    INOIS
    1.84
    imerick
    1.84
    něte
    1.83
     PUSTAKA
    1.82
     weaken
    1.75
    这里
    1.75
    präch
    1.73
    bosky
    1.73
    Activations Density 0.018%

    No Known Activations