© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67739
    Prev
    Next
    INDEX
    Explanations

    for and to

    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
     quite
    -1.10
     by
    -1.08
     things
    -1.03
    之以
    -1.00
     its
    -0.99
    asst
    -0.95
    erii
    -0.94
     film
    -0.94
    ărilor
    -0.91
     certain
    -0.90
    POSITIVE LOGITS
    !
    1.70
    !」
    1.13
    ベーション
    1.12
    !
    
    1.10
    kování
    1.09
    !"
    1.05
    !");
    1.05
     těch
    1.03
    !).
    1.03
     που
    1.03
    Activations Density 0.021%

    No Known Activations