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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72348
    Prev
    Next
    INDEX
    Explanations

    key-value pair declarations

    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
     will
    -1.39
     Indon
    -1.38
     prado
    -1.33
     vasco
    -1.31
     cristian
    -1.31
     emporio
    -1.27
     torino
    -1.21
     Issus
    -1.18
     Filipinas
    -1.16
     København
    -1.16
    POSITIVE LOGITS
     行っ
    1.14
     otros
    1.14
    ὲν
    1.09
     Insgesamt
    1.08
     Welche
    1.05
     mentiras
    1.04
    haired
    1.04
    ところは
    1.03
     disposiciones
    1.02
     Last
    1.01
    Activations Density 0.022%

    No Known Activations