© 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. 10-GEMMASCOPE-RES-131K
    7. 105238
    Prev
    Next
    INDEX
    Explanations

    recording clinical data

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

    verbs related to documenting or capturing information such as "record", "recording", and similar data collection 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
     VERY
    -2.14
    }
    -2.11
    >
    -2.09
    １
    -2.08
    \
    -2.05
    骜
    -1.98
    ↵↵
    -1.96
     I
    -1.91
    Hmmm
    -1.88
    %
    -1.87
    POSITIVE LOGITS
    豋
    2.55
    CurtirCurtir
    2.23
    欵
    2.20
    ではまた
    2.14
     permitem
    2.02
     numerous
    1.96
    勦
    1.94
     yapımı
    1.91
    Donativos
    1.91
     Küsten
    1.91
    Activations Density 0.041%

    No Known Activations