© 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. 872
    Prev
    Next
    INDEX
    Explanations

    A (Graphic) Novel

    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
     of
    -1.48
     alſo
    -1.38
     representing
    -1.37
     Эти
    -1.33
     ebenfalls
    -1.33
     estos
    -1.28
     Questi
    -1.27
    ž
    -1.24
     επίσης
    -1.23
     también
    -1.21
    POSITIVE LOGITS
     only
    1.73
     but
    1.63
     automática
    1.37
     porque
    1.37
     even
    1.35
     åp
    1.35
     mágica
    1.31
    ）
    1.31
    ("")]
    1.30
     because
    1.28
    Activations Density 0.230%

    No Known Activations