© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128484
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on words naming animal body parts (e.g. belly, eyes, tail, whiskers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    parts of the body

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

    visual elements and physical features in descriptions, such as body parts, architectural elements, and physical objects.

    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_22/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
    ּוֹ
    -1.77
    ִּ
    -1.73
    ַּ
    -1.59
     бампер
    -1.51
    ֶּ
    -1.41
     लोग
    -1.20
    ֵּ
    -1.19
    ־ה
    -1.16
    וּ
    -1.15
    וּ
    -1.13
    POSITIVE LOGITS
    ׇ
    1.47
    ちゃんと
    1.27
     گیاه
    1.20
     ویتامین
    1.15
     растения
    1.12
     borbo
    1.10
     αὐ
    1.10
     latine
    1.09
    wijl
    1.08
     ܐ
    1.07
    Activations Density 0.023%

    No Known Activations