© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111162
    Prev
    Next
    INDEX
    Explanations

    verbs followed by modifiers

    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
     zoude
    -2.47
    
    -2.27
    ACIÓN
    -2.22
    Jeudi
    -2.20
    瘊
    -2.13
    垰
    -2.03
    ACIONES
    -2.02
     bulging
    -2.00
     lamenta
    -1.99
     promove
    -1.98
    POSITIVE LOGITS
    );
    2.72
     With
    2.25
    ."
    2.13
     after
    2.05
    ";
    2.05
     '
    2.00
     as
    1.94
    ):
    1.87
    What
    1.87
    ,"
    1.84
    Activations Density 0.089%

    No Known Activations