© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    for loop constructs

    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
     ayar
    -1.11
     garcía
    -1.05
    jezd
    -1.04
     specifiche
    -1.02
    Itu
    -1.02
    Musi
    -1.01
    kön
    -0.98
    isContained
    -0.97
    sowie
    -0.97
     fré
    -0.96
    POSITIVE LOGITS
     also
    1.13
     Due
    1.12
     his
    1.09
     apoya
    1.08
    не
    1.07
     vivió
    1.03
     também
    1.02
     también
    0.98
    long
    0.96
     dessen
    0.95
    Activations Density 0.003%

    No Known Activations