© 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. 86078
    Prev
    Next
    INDEX
    Explanations

    archived, transitioning, showcased

    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
    あります
    -2.84
     During
    -2.77
    あるので
    -2.72
    ”:
    -2.69
     Unterscheidung
    -2.63
     Since
    -2.45
     Everything
    -2.44
    ה
    -2.38
     Meksika
    -2.38
     untuk
    -2.31
    POSITIVE LOGITS
    鲧
    2.88
    '
    2.84
     nothwendig
    2.77
    的我
    2.59
    的很
    2.53
    艄
    2.52
    真好
    2.52
    鬭
    2.50
    矬
    2.48
    镦
    2.44
    Activations Density 0.018%

    No Known Activations