© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    starting content titles

    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
    )))))
    -1.34
     måde
    -1.28
     dólares
    -1.28
    🏠
    -1.27
     sofá
    -1.27
    URLEncoder
    -1.25
     konflikt
    -1.24
     salonu
    -1.23
    AMENTE
    -1.23
    ♻
    -1.21
    POSITIVE LOGITS
     the
    1.35
    </b>
    1.25
    e
    1.24
    Argumento
    1.13
     too
    1.13
     need
    1.13
     чаще
    1.13
     again
    1.12
    z
    1.11
    n
    1.09
    Activations Density 0.000%

    No Known Activations