© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    H4, 4 following text

    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
     Institutionen
    -2.38
     präsenti
    -2.16
    趼
    -2.08
     wollt
    -1.88
     erhielten
    -1.84
     Frühjahr
    -1.83
    沺
    -1.83
     mußten
    -1.81
    $
    -1.80
     Forty
    -1.78
    POSITIVE LOGITS
    鼱
    2.17
    O
    2.17
    鏷
    2.17
    峮
    2.14
    д
    1.94
    圌
    1.91
    ⢪
    1.89
    
    1.88
     ſtre
    1.88
    桖
    1.88
    Activations Density 0.004%

    No Known Activations