© 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. 34-GEMMASCOPE-RES-131K
    7. 75917
    Prev
    Next
    INDEX
    Explanations

    forces, selection, acting

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

    The neuron detects mentions of physical forces (e.g. tension, gravity, acting forces) in technical or scientific text.

    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
    ⌢
    -0.79
     Verfahren
    -0.78
    クリル
    -0.77
    entrySet
    -0.75
     ショルダー
    -0.73
    järvi
    -0.73
    kében
    -0.73
    ран
    -0.68
    rítica
    -0.68
     useSelector
    -0.68
    POSITIVE LOGITS
     acting
    5.28
    acting
    4.19
     acted
    3.84
     Acting
    3.80
    Acting
    3.75
     act
    3.08
    acted
    2.83
     acts
    2.78
    作用
    2.64
     дей
    2.52
    Activations Density 0.202%

    No Known Activations