© 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. 39521
    Prev
    Next
    INDEX
    Explanations

    analytical spectrometry and mass spectrometry

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

    scientific laboratory techniques and analytical methods used for sample analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly fires on short, capitalized sequences and hyphenated tokens that name specialized analytical instruments or methods (e.g. “ICP‐MS,” “MALDI,” “EPMA,” “FNAB”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    "));
    -1.75
    /";
    -1.64
    ()));
    -1.61
    
    -1.59
    </h3>
    -1.59
    」
    -1.52
    ();
    
    -1.50
    💃
    -1.47
    €™
    -1.46
    *************/
    -1.45
    POSITIVE LOGITS
     of
    1.48
    ﺰ
    1.31
     tikai
    1.28
    ubahan
    1.17
     heal
    1.16
    Mejor
    1.15
     verheir
    1.14
     公主
    1.12
    inkgo
    1.12
     leaning
    1.11
    Activations Density 0.062%

    No Known Activations