© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    me a message

    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
     it
    -1.23
    讓人
    -1.16
    让人
    -1.13
     anyone
    -1.10
     facilmente
    -1.04
     rapidamente
    -1.04
     itself
    -1.03
     someone
    -1.03
    楽しかった
    -1.02
     mato
    -0.99
    POSITIVE LOGITS
     והוא
    1.19
    5
    1.02
    punkten
    1.01
    derdag
    1.00
    ální
    1.00
     ۱۲
    0.99
    ҳо
    0.98
     ۱۱
    0.98
    Workers
    0.98
    SPARENT
    0.98
    Activations Density 0.049%

    No Known Activations