© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130490
    Prev
    Next
    INDEX
    Explanations

    las or lasers

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

    The neuron fires on any token containing the character sequence “las” (e.g. in “lastid,” “microsplastics,” “ublas,” etc.).

    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
    愎
    -3.09
     biała
    -3.05
    摭
    -3.03
     lidé
    -2.97
    鯽
    -2.95
    jewództ
    -2.95
    ם
    -2.89
    oader
    -2.84
     něm
    -2.83
    獃
    -2.83
    POSITIVE LOGITS
    y
    5.59
    a
    5.44
    ing
    5.16
    3
    4.66
    4
    4.59
    2
    4.41
    8
    4.34
    6
    4.25
    7
    3.98
    u
    3.94
    Activations Density 0.026%

    No Known Activations