© 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. 112456
    Prev
    Next
    INDEX
    Explanations

    uterine anatomy and pathology

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

    anatomical references to the uterus or uterine system.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily detects mentions of “uterine” (i.e. references to the uterus or uterine-related terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    榈
    -2.83
     dentelle
    -2.67
    喾
    -2.63
    铼
    -2.61
    麈
    -2.56
    䛗
    -2.47
    敉
    -2.45
     bendera
    -2.41
     poussière
    -2.41
     grotte
    -2.39
    POSITIVE LOGITS
    蘩
    2.45
    u
    2.41
    न
    2.16
     publicity
    2.09
    </td>
    2.08
    ized
    2.02
    In
    1.98
    嶮
    1.97
    ing
    1.95
    <
    1.93
    Activations Density 0.005%

    No Known Activations