© 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. 58477
    Prev
    Next
    INDEX
    Explanations

    priest of or in charge

    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
     wayward
    -2.55
     haupts
    -2.55
    哙
    -2.50
    ⟞
    -2.33
    就算是
    -2.30
     isso
    -2.30
     he
    -2.30
     Creates
    -2.28
    .\
    -2.27
    拶
    -2.27
    POSITIVE LOGITS
    如果
    3.00
    🤎
    2.78
    😫
    2.73
    可以
    2.69
    🫶
    2.53
    I
    2.48
    💓
    2.45
    ❕
    2.44
    😚
    2.44
    🍻
    2.42
    Activations Density 0.003%

    No Known Activations