© 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. 84041
    Prev
    Next
    INDEX
    Explanations

    liver cells and liver tissue

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

    The neuron detects the term "hepatocyte" or related liver cell terminology in medical and scientific 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
    “,
    -3.28
    The
    -3.11
    </h3>
    -2.94
    “.
    -2.78
    ].
    -2.69
    .“
    -2.64
    ).
    -2.56
    ”.
    -2.56
    」
    -2.52
     інші
    -2.44
    POSITIVE LOGITS
    蹕
    2.69
    やりたい
    2.48
     was
    2.47
    在她
    2.44
    苼
    2.34
    楽しみにして
    2.31
    簠
    2.31
    想不到
    2.31
     potře
    2.28
    赑
    2.27
    Activations Density 0.031%

    No Known Activations