© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13468
    Prev
    Next
    INDEX
    Explanations

    sublingual and submandibular glands

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

    anatomical terms and locations in the body.

    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
    数据的
    -1.28
    迳
    -1.26
     coute
    -1.23
     课
    -1.20
    ஂ
    -1.17
    电压
    -1.12
    établir
    -1.11
     even
    -1.11
    和風
    -1.11
    嗄
    -1.10
    POSITIVE LOGITS
     industriales
    1.27
    Também
    1.26
    Bibliografía
    1.24
     клиен
    1.20
    }$
    1.19
     frucht
    1.17
     potenciales
    1.16
    ياً
    1.16
     conocidas
    1.15
    リーブ
    1.14
    Activations Density 0.057%

    No Known Activations