© 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. 22-GEMMASCOPE-RES-131K
    7. 54519
    Prev
    Next
    INDEX
    Explanations

    consider what follows

    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_22/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
    但这
    -1.17
     kotlinx
    -0.96
    évé
    -0.94
    但却
    -0.91
    .}(
    -0.91
    Edmonton
    -0.89
     doloroso
    -0.88
     lamen
    -0.88
    mmä
    -0.88
     contempl
    -0.88
    POSITIVE LOGITS
    Using
    1.11
    During
    1.09
    Given
    1.06
    ymas
    0.99
     Using
    0.98
     Given
    0.98
     lautet
    0.94
     During
    0.94
    THE
    0.91
     OGSÅ
    0.88
    Activations Density 0.001%

    No Known Activations