© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71751
    Prev
    Next
    INDEX
    Explanations

    code syntax, variable assignments

    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
     seçenek
    -1.30
     bulunabilir
    -1.29
     türkiye
    -1.29
     anahtar
    -1.26
     malzeme
    -1.26
     esempio
    -1.23
     bluz
    -1.22
     verschiedenen
    -1.20
    すっ
    -1.20
     gerekir
    -1.20
    POSITIVE LOGITS
     (
    1.55
     as
    1.48
     by
    1.45
    </em>
    1.30
     all
    1.27
    </strong>
    1.25
    تاح
    1.23
    thirds
    1.23
    </h2>
    1.20
     which
    1.20
    Activations Density 0.017%

    No Known Activations