© 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. 73156
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming 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
     transfé
    -1.11
     szczególnie
    -1.10
     viendo
    -0.96
     ningún
    -0.93
    ticularly
    -0.93
     estrategias
    -0.91
     maintenir
    -0.91
    э
    -0.90
     verkla
    -0.90
     anúncio
    -0.90
    POSITIVE LOGITS
     eccl
    1.19
    Ẓ
    0.95
    ₁(
    0.90
     decis
    0.88
    яг
    0.85
     začet
    0.83
     noyau
    0.83
     oeil
    0.83
     dle
    0.82
    chées
    0.82
    Activations Density 0.007%

    No Known Activations