© 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. 36087
    Prev
    Next
    INDEX
    Explanations

    and

    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
     vín
    -0.96
     Pero
    -0.95
    зык
    -0.94
    Slav
    -0.94
     ané
    -0.92
     interag
    -0.92
    Publik
    -0.91
     duce
    -0.90
     bás
    -0.88
     signifikan
    -0.88
    POSITIVE LOGITS
     then
    1.04
    :
    1.02
     where
    0.92
    M
    0.82
     only
    0.80
    •
    0.80
    *
    0.79
    </strong>
    0.79
     see
    0.78
    )
    0.77
    Activations Density 0.061%

    No Known Activations