© 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. 66260
    Prev
    Next
    INDEX
    Explanations

    adjuvant chemotherapy

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

    proper names of people and places, with highest activation for first names like "Stacy" and "Jodi" and place names like "Utica".

    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
    菒
    -2.69
    {
    -2.53
    霂
    -2.39
    ↵
    -2.28
     {
    -2.22
    }
    -2.17
    \
    -2.16
    $
    -2.13
    </em>
    -2.11
    蚣
    -2.09
    POSITIVE LOGITS
    蔔
    2.63
    之际
    2.36
    問題は
    2.36
    ではまた
    2.36
     standalone
    2.34
     aktiven
    2.33
    把我
    2.31
    があ
    2.31
    闔
    2.30
    with
    2.28
    Activations Density 0.026%

    No Known Activations