© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40764
    Prev
    Next
    INDEX
    Explanations

    my, your, or our things and choices

    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
     resultaten
    -1.57
     problemen
    -1.46
    																												
    -1.35
     inapropiados
    -1.28
    sä
    -1.25
    																													
    -1.24
    																														
    -1.20
    wakili
    -1.17
    ซ์
    -1.15
     másik
    -1.13
    POSITIVE LOGITS
    整整
    1.49
    }
    1.42
    啬
    1.38
     gesamten
    1.30
    layah
    1.29
     ۱۱
    1.28
     ۲۵
    1.27
     будь
    1.25
     ۳۰
    1.24
    陸上
    1.23
    Activations Density 0.031%

    No Known Activations