© 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. 9617
    Prev
    Next
    INDEX
    Explanations

    Kota Tinggi Museum, Science Concepts

    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
     from
    -1.52
    )।
    -1.30
    ֿ
    -1.23
     until
    -1.22
     and
    -1.17
     information
    -1.16
     शुर
    -1.16
     Riproduzione
    -1.14
    딪
    -1.13
     because
    -1.10
    POSITIVE LOGITS
    though
    1.30
    w
    1.16
    H
    1.12
     gänzlich
    1.11
     begrenzt
    1.11
     jarring
    1.08
    n
    1.08
    in
    1.07
     trois
    1.05
     bedingt
    1.04
    Activations Density 0.000%

    No Known Activations