© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39920
    Prev
    Next
    INDEX
    Explanations

    phase II trials

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

    clinical trial phase designations (Phase I, Phase II, Phase III) in medical research literature.

    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
    ).
    -1.83
     there
    -1.73
    猡
    -1.72
     
    -1.66
    ?
    -1.64
    (‘
    -1.59
     ANY
    -1.55
     jis
    -1.54
    ’;
    -1.54
     are
    -1.52
    POSITIVE LOGITS
    他的
    2.25
    s
    1.88
    idlertid
    1.81
     of
    1.80
    自己
    1.78
    Это
    1.73
    躄
    1.72
    ﾔ
    1.69
    𨭆
    1.67
    異なります
    1.66
    Activations Density 0.010%

    No Known Activations