© 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. 67295
    Prev
    Next
    INDEX
    Explanations

    phosphate and its chemical contexts

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

    This neuron detects the word "phosphate" and related chemical compounds.

    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
    樒
    -2.92
     Which
    -2.92
    l
    -2.67
    鬭
    -2.63
     стоимость
    -2.61
    h
    -2.59
    
    -2.58
    1
    -2.56
    慢慢的
    -2.53
    鼉
    -2.53
    POSITIVE LOGITS
    <bos>
    2.48
    2.45
    できる
    2.36
    
    2.34
    да
    2.34
    ｄ
    2.30
     resolute
    2.28
    すること
    2.27
    ｋ
    2.27
    มี
    2.25
    Activations Density 0.016%
    No Known Activations