© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    El Niño

    np_acts-logits-general · gemini-2.5-flash-lite

    four-digit years, especially in contexts related to weather, temperature records, or forecasts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Descubre
    -1.04
    ссия
    -0.85
    Aún
    -0.84
    Tienen
    -0.83
     Existen
    -0.81
     Sigue
    -0.81
     Algunos
    -0.80
    Existen
    -0.79
     Incluso
    -0.79
    Sigue
    -0.79
    POSITIVE LOGITS
     El
    3.77
    El
    3.27
     Эль
    2.16
     La
    2.14
     ENS
    1.86
    La
    1.81
     EI
    1.80
     el
    1.77
    エル
    1.73
     EL
    1.72
    Activations Density 0.032%

    No Known Activations