© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14232
    Prev
    Next
    INDEX
    Explanations

    numbers bounded by symbols

    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
    originally
    -1.09
     moſt
    -1.07
     både
    -1.07
     BEAUT
    -1.05
     thoſe
    -0.99
    mainly
    -0.98
     BEAUTIFUL
    -0.98
    揸
    -0.98
    愀
    -0.97
    mostly
    -0.97
    POSITIVE LOGITS
     strongly
    1.02
     appropriately
    1.02
     strengthen
    1.02
     For
    0.98
     all
    0.97
     aptly
    0.97
     in
    0.97
     at
    0.96
     on
    0.96
     specific
    0.93
    Activations Density 0.016%

    No Known Activations