© 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. 44667
    Prev
    Next
    INDEX
    Explanations

    behavioral research and health topics

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

    The neuron activates for the word "behavioral" in academic or medical contexts.

    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
    𝗞
    -2.58
    苌
    -2.45
    xvii
    -2.41
    攰
    -2.39
    ☆☆
    -2.39
     The
    -2.34
    久保
    -2.34
    cheduler
    -2.31
     dritte
    -2.27
    厛
    -2.23
    POSITIVE LOGITS
    _
    3.97
    M
    3.52
    B
    3.42
    V
    3.41
    R
    3.16
    W
    3.14
    O
    3.08
    Y
    3.05
    G
    3.05
    S
    3.05
    Activations Density 0.004%

    No Known Activations