© 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. 10-GEMMASCOPE-RES-131K
    7. 14073
    Prev
    Next
    INDEX
    Explanations

    used as / to explain purpose

    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
     fabrik
    -1.75
     eier
    -1.67
     aussit
    -1.52
     maler
    -1.51
     teknik
    -1.50
     spesifik
    -1.49
     flink
    -1.48
     engel
    -1.48
     gitar
    -1.47
     gewi
    -1.46
    POSITIVE LOGITS
     with
    2.05
     Although
    1.77
     Surprisingly
    1.66
     for
    1.61
     Traditionally
    1.60
     Unlike
    1.59
     With
    1.59
     While
    1.55
     without
    1.54
     Without
    1.53
    Activations Density 0.161%

    No Known Activations