© 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. 15403
    Prev
    Next
    INDEX
    Explanations

    programming keywords and code 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
    Hva
    -0.92
    Posté
    -0.90
     mestre
    -0.90
    Warna
    -0.88
    Spes
    -0.86
    usakan
    -0.85
    Ирина
    -0.85
     luta
    -0.84
     flota
    -0.83
    Cinta
    -0.83
    POSITIVE LOGITS
    </em>
    1.12
    Â
    1.01
     lutego
    0.99
    ală
    0.98
     ноября
    0.95
     мая
    0.93
     июня
    0.93
    𝗔
    0.93
     employers
    0.93
    processable
    0.93
    Activations Density 0.015%

    No Known Activations