© 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. 69301
    Prev
    Next
    INDEX
    Explanations

    pivotal movement

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

    The neuron fires on words describing mechanical pivoting or rotational movement (e.g., “pivot,” “pivotally,” “moved,” “movable”).

    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
    {},
    -1.41
    setTime
    -1.32
     entire
    -1.30
     few
    -1.29
    の方も
    -1.28
     desconoc
    -1.27
     they
    -1.26
    ⵌ
    -1.26
    девушка
    -1.25
     olduğunu
    -1.24
    POSITIVE LOGITS
     which
    1.59
    This
    1.41
     with
    1.37
    如果没有
    1.33
    If
    1.23
     sirva
    1.22
     if
    1.21
    Coppa
    1.20
     één
    1.20
     imprud
    1.20
    Activations Density 0.083%

    No Known Activations