© 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. 68984
    Prev
    Next
    INDEX
    Explanations

    technical or list item starters

    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
     vœux
    -1.00
    although
    -0.97
     plastiques
    -0.91
    terr
    -0.90
     bambú
    -0.90
     Christmas
    -0.89
    resep
    -0.88
    𝗇
    -0.88
    langsung
    -0.88
     ͡
    -0.88
    POSITIVE LOGITS
    vantaged
    1.00
    からず
    1.00
    但却
    0.96
    因为它
    0.96
    onuc
    0.96
     promont
    0.93
    却又
    0.92
    ("")]
    0.90
     ammon
    0.90
     tủ
    0.90
    Activations Density 0.000%

    No Known Activations