© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93731
    Prev
    Next
    INDEX
    Explanations

    library and software documentation referencing

    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
     eint
    -0.73
     insertion
    -0.72
     menolak
    -0.70
     Zutaten
    -0.70
     święta
    -0.69
     моего
    -0.69
     przecież
    -0.68
    droit
    -0.67
     Protecting
    -0.66
    protect
    -0.65
    POSITIVE LOGITS
     Vai
    0.70
    Configurable
    0.70
     cleanser
    0.69
     Overture
    0.68
     Greenway
    0.68
     Pils
    0.67
     fores
    0.67
    LABOR
    0.66
     compren
    0.66
    Klu
    0.65
    Activations Density 0.045%

    No Known Activations