© 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. 34-GEMMASCOPE-RES-131K
    7. 1964
    Prev
    Next
    INDEX
    Explanations

    words starting with Le

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

    The neuron selectively activates on the subword “Le” (e.g. as a standalone or word‐piece token beginning with “Le”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     pagine
    -0.89
    ี่ยม
    -0.89
    ringar
    -0.82
     Monats
    -0.82
    p
    -0.78
     meinem
    -0.77
     prevista
    -0.77
     istruzioni
    -0.75
    ect
    -0.75
    隙間
    -0.73
    POSITIVE LOGITS
     Ле
    1.34
    Le
    1.29
     Lé
    1.23
     Le
    1.23
    Ле
    1.22
    lə
    1.12
     LEV
    0.96
     obé
    0.96
     LE
    0.94
    LE
    0.93
    Activations Density 0.042%

    No Known Activations