© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68444
    Prev
    Next
    INDEX
    Explanations

    body parts and coverings

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

    nouns referring to body parts of animals and humans.

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

    The neuron strongly activates on words containing body-part terms (e.g. tail, feet, head, foot).

    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
     –
    -1.62
    ;
    -1.60
     parteci
    -1.55
    ed
    -1.46
     obiettivi
    -1.45
    </h1>
    -1.45
    .
    -1.45
     ajustable
    -1.41
    鱟
    -1.40
    </i>
    -1.39
    POSITIVE LOGITS
    </em>
    2.00
     Gründe
    1.66
    </h2>
    1.66
    ৄ
    1.59
    ,\\
    1.58
     famosas
    1.55
     Schreiben
    1.46
    荪
    1.45
     ozdob
    1.44
    samo
    1.43
    Activations Density 0.055%

    No Known Activations