© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40216
    Prev
    Next
    INDEX
    Explanations

    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
    லா
    -1.18
     recomendo
    -1.10
    dapat
    -1.08
     Livro
    -1.07
     GUIDELINES
    -1.02
     konkrét
    -1.00
    avadoc
    -0.99
    kontroll
    -0.99
    jds
    -0.99
    ORDER
    -0.98
    POSITIVE LOGITS
    Candid
    1.07
    Torna
    1.03
     Candid
    1.01
    zeczy
    0.98
     fusible
    0.97
    зык
    0.97
    igli
    0.97
     reptile
    0.95
    といった
    0.94
    兩種
    0.93
    Activations Density 0.003%

    No Known Activations