© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99136
    Prev
    Next
    INDEX
    Explanations

    physical objects and their parts

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

    The neuron detects words that express spatial relationships or three-dimensional positioning (distance, orientation, or location terms).

    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
     REALLY
    -1.45
    を使う
    -1.45
     galinha
    -1.40
     VERY
    -1.34
    uxta
    -1.32
     coelho
    -1.32
     této
    -1.31
    몀
    -1.30
     calzado
    -1.29
     этому
    -1.28
    POSITIVE LOGITS
     when
    2.27
    when
    1.96
     from
    1.91
     as
    1.89
     during
    1.81
     which
    1.72
     allowing
    1.71
     making
    1.65
     both
    1.63
     indicating
    1.63
    Activations Density 0.064%

    No Known Activations