© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    A formal Atlanta SPANISH Arrest

    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
    elektron
    -1.07
    chaise
    -1.03
    tapis
    -1.02
     persil
    -1.01
    sepatu
    -0.98
    violin
    -0.96
    ysl
    -0.95
    mermaid
    -0.94
    umpulkan
    -0.93
    thiet
    -0.93
    POSITIVE LOGITS
    ore
    1.05
    ath
    1.05
    in
    1.05
    mator
    1.04
    dia
    1.02
    men
    1.02
    nin
    1.02
     BIBLIOGRAPHY
    0.99
    chi
    0.97
    kar
    0.96
    Activations Density 0.000%

    No Known Activations