© 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. 74466
    Prev
    Next
    INDEX
    Explanations

    true qualifier

    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
    ilización
    -1.32
    </strong>
    -1.18
    厦门
    -1.10
     oseb
    -1.09
     ?
    -1.05
    朝から
    -1.05
    ización
    -1.05
     lifes
    -1.02
     idén
    -1.02
    了出来
    -1.02
    POSITIVE LOGITS
     also
    1.55
    '
    1.48
    true
    1.45
    真正
    1.30
     true
    1.27
    peech
    1.24
     verdadeiro
    1.21
     مانند
    1.19
    rato
    1.16
     only
    1.14
    Activations Density 0.061%

    No Known Activations