© 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. 34-GEMMASCOPE-RES-131K
    7. 56675
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and movement

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

    This neuron responds to Swedish words (i.e. it flags tokens from Swedish text) rather than English.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     cuotas
    -0.93
    ቕ
    -0.93
     dépens
    -0.92
    Материал
    -0.91
    Только
    -0.88
    Haiti
    -0.86
    Дизайн
    -0.85
    espé
    -0.85
    Мі
    -0.85
    ține
    -0.85
    POSITIVE LOGITS
     away
    1.43
     out
    1.38
     into
    1.16
     up
    1.09
     off
    0.97
     down
    0.97
    出
    0.89
    愈
    0.88
     aside
    0.85
    мами
    0.85
    Activations Density 0.006%

    No Known Activations