© 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. 10-GEMMASCOPE-RES-131K
    7. 42481
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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_10/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
     to
    -1.39
     щоб
    -1.38
    /**
    -1.31
     Diman
    -1.31
     ziyaretçi
    -1.30
    )=\
    -1.23
    ORETICAL
    -1.21
    来越
    -1.20
    ilisation
    -1.20
     jego
    -1.17
    POSITIVE LOGITS
     prüfen
    1.46
     is
    1.45
     says
    1.32
     größten
    1.32
     allows
    1.30
     both
    1.29
     verhindern
    1.28
    !
    1.28
     allow
    1.23
    ֽ
    1.23
    Activations Density 0.349%

    No Known Activations