© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    the way that

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

    This neuron fires on the word “that” (and similar discourse markers) when it introduces a subordinate or explanatory clause.

    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
    </h3>
    -1.98
    黩
    -1.89
     pretože
    -1.67
    阵法
    -1.64
    𝔇
    -1.63
    Composición
    -1.63
     scoperta
    -1.56
    下意识
    -1.52
     parro
    -1.52
    ⟣
    -1.52
    POSITIVE LOGITS
    </b>
    1.70
    ViewChild
    1.65
     Hivatalos
    1.52
    $
    1.50
     và
    1.48
     town
    1.46
     życiu
    1.46
     設計
    1.45
     crimes
    1.44
    如有
    1.44
    Activations Density 0.012%

    No Known Activations