© 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. 59436
    Prev
    Next
    INDEX
    Explanations

    body parts and structures

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

    body parts and anatomical terms in medical or biological texts.

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

    This neuron identifies anatomical terms—mentions of body parts, organs, or specific bodily regions.

    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
    localObject
    -1.22
     volando
    -1.20
    çou
    -1.16
    ства
    -1.16
     kahit
    -1.12
    ))).
    -1.10
    tovat
    -1.10
     tager
    -1.09
    長の
    -1.09
    řízení
    -1.09
    POSITIVE LOGITS
    Aunque
    1.45
    Estos
    1.41
     of
    1.31
     của
    1.22
    ของ
    1.21
    Some
    1.19
     It
    1.16
     where
    1.15
    Cuando
    1.14
     appelez
    1.13
    Activations Density 0.206%

    No Known Activations