© 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. 10-GEMMASCOPE-RES-131K
    7. 86213
    Prev
    Next
    INDEX
    Explanations

    diving, temperature, water quality

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

    references to aquatic or underwater environments and activities.

    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_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
     voorbeeld
    -1.16
     mehrere
    -1.13
     romero
    -1.09
    ﺖ
    -1.08
     může
    -1.05
    Importer
    -1.03
    NSP
    -1.01
     vuonna
    -1.01
     gaun
    -0.99
     显
    -0.97
    POSITIVE LOGITS
     day
    1.16
     aún
    1.08
     overall
    1.08
    ут
    1.07
    lamó
    1.05
    endő
    1.04
     acessar
    1.03
    반
    1.02
     ayud
    1.01
    зани
    1.01
    Activations Density 0.043%

    No Known Activations