© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    French words starting with A, E, I, O, U

    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
    If
    -2.55
    When
    -2.27
     Ironically
    -2.22
    蛻
    -2.22
    jących
    -2.14
    Since
    -2.11
     eliminating
    -2.08
     Almost
    -2.08
    ﾛ
    -2.06
     Regardless
    -2.05
    POSITIVE LOGITS
    "
    3.42
    轳
    2.70
     brazen
    2.56
     myriad
    2.45
    }
    2.42
    都已经
    2.33
    鼋
    2.33
    '
    2.30
    .'
    2.23
    操控
    2.23
    Activations Density 0.006%

    No Known Activations