© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98927
    Prev
    Next
    INDEX
    Explanations

    damp, damping, damper

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

    The neuron specializes in detecting technical engineering terms for mechanical damping, clamping, and related tension components.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     exposiciones
    -2.44
    栊
    -2.34
     labores
    -2.17
    Ꮟ
    -2.11
     Acuerdo
    -2.09
    に於
    -2.05
     invitaciones
    -2.03
     Süden
    -2.02
     Granted
    -2.02
     reseñas
    -2.02
    POSITIVE LOGITS
     榜
    2.23
    ൎ
    2.16
     礼
    2.14
    毐
    2.09
    檍
    2.06
     药
    2.03
     宫
    2.00
                    
    1.99
    \
    1.98
    耵
    1.94
    Activations Density 0.004%

    No Known Activations