© 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. 66096
    Prev
    Next
    INDEX
    Explanations

    command line options

    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
     recently
    -1.09
     of
    -1.07
     recent
    -1.05
     недавно
    -1.02
     your
    -1.02
    Your
    -1.01
     current
    -1.00
    btnBack
    -0.98
     my
    -0.98
     this
    -0.97
    POSITIVE LOGITS
     hedef
    1.04
     PrintWriter
    1.04
     instead
    1.00
    嫻
    0.99
     fonctionnalités
    0.96
    rimiento
    0.94
    roids
    0.94
    чительно
    0.94
    めていた
    0.94
     WebElement
    0.93
    Activations Density 0.009%

    No Known Activations