© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57662
    Prev
    Next
    INDEX
    Explanations

    athletic and graceful movement

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

    This neuron activates on words that describe athletic or physical-ability attributes (e.g., athleticism, acrobatic, gangly, graceful).

    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
     they
    -1.30
    Loading
    -1.23
    \
    -1.20
     "",
    -1.13
    .,
    -1.12
     =>
    -1.09
    $,
    -1.09
     Nachweis
    -1.07
     Änder
    -1.07
     boxeo
    -1.06
    POSITIVE LOGITS
     acrobat
    1.28
    诘
    1.24
    ﻒ
    1.22
    互联网档案馆
    1.21
     doomed
    1.20
    籟
    1.19
    nicamente
    1.17
     einiges
    1.16
    estão
    1.16
    чника
    1.16
    Activations Density 0.034%

    No Known Activations