© 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. 73748
    Prev
    Next
    INDEX
    Explanations

    java programming imports

    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
     fré
    -1.26
     its
    -1.23
    感じで
    -1.15
     capot
    -1.11
    ほら
    -1.11
    事が
    -1.10
    あぁ
    -1.09
    MERCIAL
    -1.09
    者に
    -1.08
     retira
    -1.07
    POSITIVE LOGITS
    了许多
    1.13
    除此
    1.05
    دانلود
    1.01
     teller
    0.97
    <bos>
    0.97
    🦤
    0.94
    서는
    0.94
    と思いました
    0.93
    ka
    0.92
    Herzlich
    0.91
    Activations Density 0.001%

    No Known Activations