© 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. 34-GEMMASCOPE-RES-131K
    4. 75965
    Prev
    Next
    INDEX
    Explanations

    circular and turbulent motion

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

    The neuron detects words referring to swirling or vortex‐like motion (e.g. swirl, whirlpool, cyclone, whirlwind, vortex).

    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
     crawling
    -0.82
     meman
    -0.79
    neval
    -0.77
     parade
    -0.76
    焰
    -0.74
    ศึกษา
    -0.73
    ზ
    -0.73
     prosecution
    -0.73
    TRANSM
    -0.73
    varchar
    -0.72
    POSITIVE LOGITS
     vortex
    2.42
     whirlwind
    2.23
     whirl
    2.17
     tornado
    2.02
     whirlpool
    2.00
     cyclone
    1.92
     whirling
    1.83
     swirl
    1.80
    vortex
    1.79
     whir
    1.75
    Activations Density 0.025%

    No Known Activations