© 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. 93018
    Prev
    Next
    INDEX
    Explanations

    code keywords and functions

    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
     bluza
    -1.17
     trajets
    -1.17
     amely
    -1.16
     pantalón
    -1.13
     parachoque
    -1.12
     claramente
    -1.10
     vín
    -1.08
    UCKER
    -1.08
    取った
    -1.07
     which
    -1.06
    POSITIVE LOGITS
     if
    2.06
    if
    1.47
     when
    1.16
     ,
    1.07
     sometimes
    1.05
     for
    1.04
     now
    1.03
     because
    1.03
     while
    1.02
     если
    1.02
    Activations Density 0.003%

    No Known Activations