© 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. 22-GEMMASCOPE-RES-131K
    7. 64869
    Prev
    Next
    INDEX
    Explanations

    dyspepsia, -osis, -itis, -oma, -ia

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

    medical condition names and terminology.

    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
     and
    -2.67
    にします
    -2.14
    の方に
    -2.11
    為に
    -2.11
     or
    -2.03
    ごとの
    -1.98
    づけ
    -1.94
    様な
    -1.93
    からお
    -1.91
    つづく
    -1.85
    POSITIVE LOGITS
    <bos>
    3.14
    がありますが
    2.11
    を
    2.09
    但却
    2.03
    って思
    1.98
    ？』
    1.94
    ですが
    1.90
    そして
    1.89
    っけ
    1.85
    なので
    1.81
    Activations Density 0.178%

    No Known Activations