© 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. 73537
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
     menyen
    -1.85
     rése
    -1.85
    PENDAHULUAN
    -1.81
    鱨
    -1.73
     مانت
    -1.70
     aspek
    -1.59
     willen
    -1.59
     incrí
    -1.57
     risiko
    -1.55
     parfü
    -1.55
    POSITIVE LOGITS
     make
    2.55
     use
    2.34
     take
    2.25
     keep
    2.20
     put
    2.16
     give
    2.09
     try
    2.09
     add
    1.93
     ensure
    1.91
     don
    1.90
    Activations Density 0.046%

    No Known Activations