© 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. 130947
    Prev
    Next
    INDEX
    Explanations

    positive definite symmetric matrix

    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
    -1.20
     effettu
    -1.03
     приме
    -1.01
    pout
    -0.98
    ixar
    -0.97
    тическая
    -0.96
    ecar
    -0.95
    continued
    -0.94
    adog
    -0.93
    蠕
    -0.91
    POSITIVE LOGITS
     вони
    1.09
    بله
    1.02
     sosis
    1.02
    lemek
    1.01
     gorro
    0.98
    ítica
    0.96
     réputation
    0.96
    شما
    0.95
     médaille
    0.94
     tensor
    0.93
    Activations Density 0.022%

    No Known Activations