© 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. 99834
    Prev
    Next
    INDEX
    Explanations

    domain suffixes like .com or .org

    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
    :
    -2.20
    -
    -2.02
    ...
    -1.96
    *"
    -1.95
    te
    -1.92
    In
    -1.82
     –
    -1.81
    '
    -1.77
    .........
    -1.75
    *'
    -1.75
    POSITIVE LOGITS
     étendue
    2.08
    じゃないですか
    2.03
    🧌
    2.02
    かと思います
    2.00
    〜！
    1.97
     丼
    1.96
    </h2>
    1.96
    
    1.95
    かなぁ
    1.92
    (*^^*)
    1.90
    Activations Density 0.030%

    No Known Activations