© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    file path components

    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
     earlier
    -1.30
     subió
    -1.07
     last
    -1.06
    caucasian
    -1.05
    tagena
    -1.05
    klere
    -1.02
    lentes
    -1.01
     Katalog
    -1.01
    geox
    -1.00
     proteínas
    -1.00
    POSITIVE LOGITS
    _
    1.27
    finally
    1.13
    🍔
    1.09
     Sarkozy
    1.06
    </i>
    1.05
    使其
    1.03
     sark
    1.02
     -
    1.02
     ￥
    1.01
    鷺
    1.00
    Activations Density 0.192%

    No Known Activations