© 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. 34-GEMMASCOPE-RES-131K
    7. 99852
    Prev
    Next
    INDEX
    Explanations

    Ebola virus, ethylene dichloride, ejection fraction

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

    terms related to diseases, technology protocols, and medical measurements.

    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_34/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
    AT
    -1.07
    毫无
    -0.97
    very
    -0.97
    有不少
    -0.96
     siguen
    -0.95
    than
    -0.94
     ebay
    -0.94
    ニク
    -0.93
    Looking
    -0.93
    asy
    -0.91
    POSITIVE LOGITS
    ?".
    1.04
     brute
    1.03
    XFF
    0.94
     berdua
    0.94
     kullanılan
    0.94
    ཫ
    0.92
    $--
    0.92
     probable
    0.92
    '".
    0.91
     huom
    0.91
    Activations Density 0.235%

    No Known Activations