© 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. 40618
    Prev
    Next
    INDEX
    Explanations

    surgical injury and environment

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

    names of physical objects or technical components, especially in legal, medical, or technical documents.

    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
    着一个
    -1.74
    𓆏
    -1.63
    了一個
    -1.48
     opulent
    -1.44
     député
    -1.43
    ܇
    -1.42
    
    -1.41
     alho
    -1.41
    ebly
    -1.40
     trône
    -1.39
    POSITIVE LOGITS
    Both
    1.81
    After
    1.81
    When
    1.76
    During
    1.70
     with
    1.70
    With
    1.69
     when
    1.60
     and
    1.55
     what
    1.53
    Each
    1.52
    Activations Density 0.185%

    No Known Activations