© 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. 43251
    Prev
    Next
    INDEX
    Explanations

    code starting signals

    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
     обеспечение
    -2.20
     Then
    -2.05
     findet
    -2.03
     olmayan
    -2.02
     Immediately
    -1.99
    籏
    -1.98
     AND
    -1.95
     kleinen
    -1.94
     otras
    -1.94
     This
    -1.94
    POSITIVE LOGITS
    鿬
    2.56
     排骨
    2.38
     própri
    2.31
    鱨
    2.16
     菇
    2.16
     prachtig
    2.14
    还想
    2.11
     camiset
    2.11
    橚
    2.09
    ᕱ
    2.08
    Activations Density 0.000%

    No Known Activations