© 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. 19933
    Prev
    Next
    INDEX
    Explanations

    do what

    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
     bordado
    -1.68
    鼇
    -1.48
    coating
    -1.44
     almofada
    -1.44
    ympto
    -1.41
    錞
    -1.40
    liability
    -1.39
    pography
    -1.38
     UIAlert
    -1.37
    珝
    -1.37
    POSITIVE LOGITS
     =
    1.38
     \
    1.33
     —
    1.28
    系の
    1.25
    }$
    1.23
    !”
    1.23
     we
    1.21
     oamen
    1.20
    %,
    1.19
      
    1.14
    Activations Density 0.021%

    No Known Activations