© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91642
    Prev
    Next
    INDEX
    Explanations

    Bura Bora Burry Breum Borregaard

    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
    Descargar
    -0.79
    ItemStack
    -0.73
     ボックス
    -0.73
    quién
    -0.73
     soledad
    -0.72
     effort
    -0.72
     críticos
    -0.70
     faço
    -0.70
    epam
    -0.70
     anyone
    -0.70
    POSITIVE LOGITS
    시아
    0.75
     esi
    0.73
    тек
    0.73
    Tro
    0.73
    Navigate
    0.72
    ätzen
    0.71
     пластик
    0.71
     Prospect
    0.70
     tillbaka
    0.70
     samtidigt
    0.69
    Activations Density 0.030%

    No Known Activations