© 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. 101376
    Prev
    Next
    INDEX
    Explanations

    medical substances or conditions

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

    references to quantities, doses, or measurements using "of" followed by a substance or entity.

    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
    馴
    -1.46
    知る
    -1.44
    評判
    -1.39
    电梯
    -1.38
    离去
    -1.34
     sopa
    -1.34
    礎
    -1.34
     seines
    -1.34
    齟
    -1.33
    这只
    -1.32
    POSITIVE LOGITS
     какой
    1.77
    2
    1.51
     zufried
    1.50
    3
    1.47
    8
    1.45
    liputi
    1.43
     entsprechende
    1.38
    𝘵
    1.35
    9
    1.35
    沨
    1.34
    Activations Density 0.162%

    No Known Activations