© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130077
    Prev
    Next
    INDEX
    Explanations

    orthogonal projections and angles

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

    The neuron fires on mentions of orthogonality—e.g. “orthogonal,” “orthonormal,” “perpendicular,” or “right angle.”

    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
     sarcas
    -1.72
     exorbit
    -1.50
    ia
    -1.50
     ʻ
    -1.46
    ﭽ
    -1.45
     oft
    -1.45
     >/
    -1.41
     инстру
    -1.38
     vele
    -1.35
    GETHER
    -1.35
    POSITIVE LOGITS
    with
    1.72
    With
    1.65
    There
    1.64
    \
    1.63
    It
    1.62
    dateTimePicker
    1.52
    Only
    1.52
     прошли
    1.50
     With
    1.46
    If
    1.45
    Activations Density 0.023%

    No Known Activations