© 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. 70990
    Prev
    Next
    INDEX
    Explanations

    COMMONWEALTH

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

    The neuron consistently activates on the word “we,” marking occurrences of that pronoun.

    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
    ’
    -3.09
    -2.97
    X
    -2.78
    What
    -2.72
    C
    -2.63
    </sup>
    -2.63
    H
    -2.63
    在
    -2.59
    W
    -2.58
    }$
    -2.56
    POSITIVE LOGITS
     unsere
    2.95
    ⢌
    2.88
    隄
    2.72
    缡
    2.66
    錞
    2.64
    transQ
    2.61
    壜
    2.56
    ครื่อง
    2.52
     ใน
    2.50
    媪
    2.50
    Activations Density 0.008%

    No Known Activations