© 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. 34-GEMMASCOPE-RES-131K
    7. 76613
    Prev
    Next
    INDEX
    Explanations

    verbs and location names

    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
    Definitely
    -1.12
    television
    -1.04
     carefree
    -1.03
    Normally
    -1.02
     craftsman
    -1.02
     colourful
    -1.00
     envisaged
    -0.97
    Nonetheless
    -0.95
     subray
    -0.94
     WEEKEND
    -0.94
    POSITIVE LOGITS
     commenced
    1.13
    ouchers
    0.87
     моз
    0.87
     ordenador
    0.86
     commencing
    0.86
     embraced
    0.85
     peculiarities
    0.85
     colored
    0.85
     intensa
    0.85
     politicians
    0.84
    Activations Density 0.037%

    No Known Activations