© 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. 70868
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
     включает
    -1.05
    onames
    -1.03
    struzioni
    -1.02
    襁
    -1.02
     Ländern
    -1.01
    colori
    -1.00
    riotic
    -1.00
     reconocido
    -0.99
    囁
    -0.96
     reconocidos
    -0.95
    POSITIVE LOGITS
    </strong>
    1.30
    </
    1.25
    ”，
    1.22
    ,”
    1.20
    </b>
    1.13
    ）
    1.11
     spurred
    1.05
    最后
    1.04
    :
    1.03
     hopefully
    1.01
    Activations Density 0.012%

    No Known Activations