© 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. 105545
    Prev
    Next
    INDEX
    Explanations

    examples introduced by e.g

    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
    fordshire
    -1.96
    il
    -1.88
    la
    -1.83
    G
    -1.78
    葙
    -1.77
    utenants
    -1.77
    ścioła
    -1.75
    nyard
    -1.73
    mindedness
    -1.69
     is
    -1.68
    POSITIVE LOGITS
    verstanden
    2.08
    When
    2.08
    Despite
    1.95
    publik
    1.91
    瀟
    1.87
    cestors
    1.86
    德國
    1.85
    During
    1.83
     their
    1.81
    Sometimes
    1.79
    Activations Density 0.033%

    No Known Activations