© 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. 84250
    Prev
    Next
    INDEX
    Explanations

    phyto- prefix with scientific terms

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

    The neuron identifies scientific terms with the prefix "phyto-" such as phytochemical, phytotherapy, phytoremediation, and phytotechnology.

    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
    );
    -2.42
    縯
    -2.33
    ();
    -2.16
    z
    -2.08
    with
    -2.06
     provides
    -2.00
    which
    -1.95
    us
    -1.94
    m
    -1.91
    ",
    -1.91
    POSITIVE LOGITS
    谖
    2.02
     But
    1.95
     начали
    1.94
    zmm
    1.93
     muerta
    1.91
     wußte
    1.91
     gebeten
    1.91
     好看
    1.89
    这里
    1.88
    yyj
    1.88
    Activations Density 0.016%

    No Known Activations