© 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. 34-GEMMASCOPE-RES-131K
    7. 58912
    Prev
    Next
    INDEX
    Explanations

    configuration, data, goals, accuracy

    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_34/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
    </u>
    -0.96
     disposiciones
    -0.92
     segni
    -0.91
    _
    -0.91
    ’
    -0.88
     acolo
    -0.88
     oportunidade
    -0.87
    worldly
    -0.87
     zweck
    -0.86
     corpi
    -0.86
    POSITIVE LOGITS
     and
    1.53
    бера
    1.03
    GZIP
    1.00
    延续
    0.92
    轢
    0.91
     tomar
    0.91
    сован
    0.89
    🤙
    0.88
    !（
    0.85
     sexto
    0.85
    Activations Density 0.622%

    No Known Activations