© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    magazine titles

    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
     rechnen
    -1.45
    .,
    -1.40
     incluso
    -1.37
    1
    -1.36
    0
    -1.35
     Kiedy
    -1.34
     Bardzo
    -1.31
    )$
    -1.30
     entspricht
    -1.27
     Dzięki
    -1.24
    POSITIVE LOGITS
    錚
    1.80
    dámské
    1.55
    pulseira
    1.48
     turist
    1.36
    结语
    1.35
    出了一
    1.34
    Где
    1.32
    تفسير
    1.31
     soupe
    1.30
    讥
    1.30
    Activations Density 0.036%

    No Known Activations