© 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. 75182
    Prev
    Next
    INDEX
    Explanations

    passed exam or milestone

    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
    baine
    -1.09
    </em>
    -1.08
    ：……
    -1.05
     Allegretto
    -1.01
     Andante
    -1.00
    世纪
    -0.98
     godine
    -0.96
     speciale
    -0.92
     Escola
    -0.92
    </h3>
    -0.92
    POSITIVE LOGITS
    Fakta
    1.39
    Gön
    1.24
    哈哈哈哈
    1.21
     ajudá
    1.21
    Komentar
    1.16
    luiting
    1.15
     reduzir
    1.13
    Kenapa
    1.13
    Kontra
    1.13
    Semoga
    1.11
    Activations Density 0.045%

    No Known Activations