© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85589
    Prev
    Next
    INDEX
    Explanations

    fatty acids, antibiotics, bankruptcy

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

    words related to scientific or technical substances and compounds, particularly fatty acids, antibiotics, and chemicals.

    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
    :
    -1.77
     also
    -1.63
     but
    -1.47
     of
    -1.38
     even
    -1.36
    /
    -1.27
     Müll
    -1.26
     utilizarse
    -1.22
     fidanz
    -1.22
    .”
    -1.22
    POSITIVE LOGITS
    kommt
    1.35
    綑
    1.31
     geleden
    1.31
     невозможно
    1.30
     nasz
    1.28
     préoccup
    1.22
     nasze
    1.20
    🚷
    1.19
    operable
    1.19
     peruan
    1.17
    Activations Density 0.601%

    No Known Activations