© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31609
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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_34/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
    лить
    -0.76
     docx
    -0.76
    cleos
    -0.74
     forskellige
    -0.71
    商城
    -0.71
     DEVICE
    -0.70
     Ramesh
    -0.70
    cadeira
    -0.68
     palais
    -0.68
     право
    -0.68
    POSITIVE LOGITS
     minimum
    1.24
     Minimum
    1.15
    Minimum
    1.13
    getMin
    1.06
    MINIMUM
    1.03
    min
    1.01
     min
    1.01
     mínimo
    0.99
    Smallest
    0.97
     smallest
    0.96
    Activations Density 0.021%

    No Known Activations