© 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. 85480
    Prev
    Next
    INDEX
    Explanations

    inguinal, groin, angiotensin, names, mines

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

    This neuron identifies anatomical and medical terms, particularly focusing on body parts like "groin," "inguinal," and terms related to the angiotensin system.

    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
    <td>
    -2.78
    <i>
    -2.73
    ,”
    -2.69
     rheinland
    -2.64
    With
    -2.64
    ):
    -2.56
     Gästen
    -2.56
        
    -2.50
    And
    -2.47
    There
    -2.47
    POSITIVE LOGITS
     gavetas
    2.55
    猹
    2.50
     frança
    2.48
    醅
    2.48
    艄
    2.47
     faune
    2.45
    聍
    2.45
    ၟ
    2.45
    ⃨
    2.45
    渽
    2.44
    Activations Density 0.008%

    No Known Activations