© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86457
    Prev
    Next
    INDEX
    Explanations

    related to

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

    The neuron strongly activates on the word “related” (especially in the phrase “related to”).

    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
    ."
    -2.42
    derdag
    -2.03
    esperienza
    -1.98
    на
    -1.91
     warped
    -1.88
    ibouti
    -1.85
    Thirty
    -1.80
    zystać
    -1.79
    ropical
    -1.79
    Three
    -1.79
    POSITIVE LOGITS
    ↵
    2.00
    it
    1.95
    a
    1.91
    我没有
    1.88
    ⧠
    1.88
    ar
    1.87
    H
    1.85
    </strong>
    1.84
     seamlessly
    1.80
    汌
    1.80
    Activations Density 0.064%

    No Known Activations