© 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. 38979
    Prev
    Next
    INDEX
    Explanations

    organic fluorine compounds and derivatives

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

    chemical compound structures and formulas in scientific 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
     these
    -2.27
     этих
    -2.19
    These
    -1.95
     they
    -1.87
    these
    -1.86
     çünkü
    -1.84
     THESE
    -1.80
     this
    -1.70
     každý
    -1.67
    Which
    -1.64
    POSITIVE LOGITS
     with
    2.16
     after
    2.05
     without
    1.88
     before
    1.88
     from
    1.78
     државе
    1.75
    嬪
    1.70
     לאחר
    1.63
     ње
    1.56
     према
    1.56
    Activations Density 0.017%

    No Known Activations