© 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. 128576
    Prev
    Next
    INDEX
    Explanations

    document section titles

    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
    킁
    -1.84
    
    -1.58
    
    -1.49
     tişört
    -1.48
    
    -1.47
     delightful
    -1.46
     torba
    -1.44
     kader
    -1.44
     decoracion
    -1.42
    
    -1.42
    POSITIVE LOGITS
     to
    1.63
     While
    1.63
     gets
    1.63
     Since
    1.62
     Although
    1.57
    ,
    1.57
     as
    1.56
     Numerous
    1.55
     because
    1.48
     Some
    1.48
    Activations Density 0.074%

    No Known Activations