© 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. 22-GEMMASCOPE-RES-131K
    4. 36623
    Prev
    Next
    INDEX
    Explanations

    corresponding elements by index

    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
     to
    -1.11
     it
    -1.07
     if
    -1.02
     dentro
    -0.88
     will
    -0.88
     so
    -0.85
     within
    -0.85
     र
    -0.78
     now
    -0.77
    IP
    -0.77
    POSITIVE LOGITS
     both
    2.22
     BOTH
    1.88
    Both
    1.85
    both
    1.75
     beider
    1.65
     Both
    1.63
     दोनों
    1.63
     både
    1.61
     beide
    1.46
     beiden
    1.41
    Activations Density 0.009%

    No Known Activations