© 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. 27432
    Prev
    Next
    INDEX
    Explanations

    code tokens followed by semicolon

    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
    -1.04
    čas
    -0.92
     усі
    -0.91
     vinculado
    -0.89
     &
    -0.89
     incorporado
    -0.87
     разные
    -0.86
     hinzugefügt
    -0.85
     muelle
    -0.85
     localizado
    -0.83
    POSITIVE LOGITS
     auge
    1.09
     transparentes
    1.07
     havi
    1.06
     Appell
    1.06
     Kalimantan
    1.06
     ladd
    1.04
     GRATU
    1.04
     heyday
    1.04
    秾
    1.03
    laubnis
    1.02
    Activations Density 0.018%

    No Known Activations