© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14200
    Prev
    Next
    INDEX
    Explanations

    flanking or both sides

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

    This neuron detects expressions describing the two sides or ends of something (e.g. “either side of,” “both sides of,” “ends”).

    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
     all
    -1.42
    ñador
    -1.29
     that
    -1.27
    已经是
    -1.25
     would
    -1.24
    日から
    -1.21
    Because
    -1.20
     is
    -1.20
    ing
    -1.19
     всех
    -1.18
    POSITIVE LOGITS
    إذا
    1.36
     ozdob
    1.31
    Και
    1.30
     trochu
    1.30
     čaj
    1.29
    illants
    1.27
     různ
    1.27
    blusa
    1.25
     jovem
    1.24
     dvě
    1.24
    Activations Density 0.095%

    No Known Activations