© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78806
    Prev
    Next
    INDEX
    Explanations

    foreign language segments

    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
     Câmara
    -1.01
    ʧ
    -0.95
    gameOver
    -0.92
     bleue
    -0.92
     maglia
    -0.90
    尙
    -0.90
     Essential
    -0.89
     regarder
    -0.86
     essential
    -0.85
    коль
    -0.85
    POSITIVE LOGITS
     mittlerweile
    1.05
     Zudem
    0.98
    色々な
    0.96
     ligeramente
    0.94
     poté
    0.93
     Gleichzeitig
    0.93
    全体の
    0.92
     жы
    0.91
     огромное
    0.90
     Besonders
    0.90
    Activations Density 0.003%

    No Known Activations