© 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. 10-GEMMASCOPE-RES-131K
    7. 58487
    Prev
    Next
    INDEX
    Explanations

    longitudinal study designs

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

    The neuron detects the word "longitudinal" in academic or scientific contexts, particularly in study descriptions.

    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
    镦
    -2.55
    
    -2.22
    aimeJ
    -2.22
     Meksiko
    -2.14
    vantaged
    -2.09
     Sénégal
    -2.08
    詎
    -2.08
     satunya
    -2.06
    鬭
    -2.03
    缯
    -2.03
    POSITIVE LOGITS
    ↵
    3.38
    </b>
    2.70
     \&
    2.67
    紧接着
    2.58
    这也是
    2.42
    同时也
    2.42
     bieten
    2.33
    \_
    2.27
     \
    2.19
    n
    2.17
    Activations Density 0.009%

    No Known Activations