© 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. 13000
    Prev
    Next
    INDEX
    Explanations

    words starting with la

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

    The neuron is triggered by the two‐letter string “la” (i.e. tokens or token fragments beginning with “la”).

    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
    ⬮
    -3.14
    蜮
    -3.03
    摭
    -2.78
    衚
    -2.73
    嘞
    -2.73
    
    -2.64
     mohou
    -2.63
    ﻒ
    -2.58
    淯
    -2.58
     motocicletas
    -2.58
    POSITIVE LOGITS
    ”
    3.59
    la
    3.36
    >
    3.34
    0
    3.31
    ↵
    3.05
    (
    3.00
    ’
    2.95
    or
    2.94
    *
    2.91
    ла
    2.86
    Activations Density 0.027%

    No Known Activations