© 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. 60934
    Prev
    Next
    INDEX
    Explanations

    policy making and implications

    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
    StoryboardSegue
    -2.39
     permettent
    -1.71
     elegan
    -1.70
     […]
    -1.70
     zahlreiche
    -1.66
    杙
    -1.59
    說
    -1.57
    ('/')
    -1.56
    ’
    -1.56
    除此之外
    -1.53
    POSITIVE LOGITS
    }$
    1.80
     ก็
    1.80
    也
    1.76
     Trouvez
    1.70
    されない
    1.68
     також
    1.62
     pikir
    1.62
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.61
    <td>
    1.60
     pasajeros
    1.60
    Activations Density 0.012%

    No Known Activations