© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36379
    Prev
    Next
    INDEX
    Explanations

    code structures and data

    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_22/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
     Both
    -0.91
     Verbesserung
    -0.90
     Companies
    -0.87
     provisions
    -0.84
     दोनों
    -0.82
     both
    -0.80
    ultor
    -0.80
     ainda
    -0.80
     BOTH
    -0.79
    changers
    -0.79
    POSITIVE LOGITS
     they
    1.05
     interpreta
    1.01
    geln
    1.01
    ентов
    1.00
     these
    0.99
    dragen
    0.91
     them
    0.89
    Specifik
    0.89
    iennes
    0.88
    owna
    0.88
    Activations Density 0.001%

    No Known Activations