© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    rotation and spin

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

    The neuron is detecting technical terms related to rotation or angular motion (e.g. spin, rotating, angular, torque, oscillation around an axis).

    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
     to
    -1.60
    ילות
    -1.42
     devem
    -1.41
     Ibidem
    -1.39
     precisam
    -1.38
     αυτή
    -1.36
     Diſ
    -1.32
    夲
    -1.30
     カジュアル
    -1.30
    為に
    -1.30
    POSITIVE LOGITS
     बहुत
    1.48
     Some
    1.43
     sehr
    1.42
     Probleme
    1.34
     As
    1.34
     अच्छी
    1.27
     Like
    1.23
     pierwszy
    1.22
    About
    1.22
    </strong>
    1.22
    Activations Density 0.042%

    No Known Activations