© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25913
    Prev
    Next
    INDEX
    Explanations

    threading in code

    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
     вже
    -1.57
    
    -1.50
     creado
    -1.49
     their
    -1.43
     differs
    -1.42
    sibili
    -1.41
     всіх
    -1.40
     follows
    -1.40
     informée
    -1.37
     travaillons
    -1.34
    POSITIVE LOGITS
    ,
    1.33
    ↵↵
    1.31
    1.27
    O
    1.23
    ↵
    1.23
     &
    1.19
    。

    1.19
    </u>
    1.17
    ↵↵↵
    1.13
    故事
    1.13
    Activations Density 0.001%
    No Known Activations