© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15960
    Prev
    Next
    INDEX
    Explanations

    chronic conditions

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

    subjects or participants in scientific or medical research studies.

    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_22/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
     endast
    -0.88
    酚
    -0.84
    iris
    -0.77
     Ghe
    -0.77
     výsled
    -0.73
     tha
    -0.73
     treas
    -0.71
     cả
    -0.71
    Momentum
    -0.70
     whit
    -0.70
    POSITIVE LOGITS
     inherent
    0.83
     vốn
    0.80
    всегда
    0.79
     constitutive
    0.78
    寐
    0.77
     hereditary
    0.75
     заранее
    0.75
     subscribed
    0.75
     翻
    0.74
    нении
    0.74
    Activations Density 0.160%

    No Known Activations