© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    thereof

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

    The neuron detects formal legal or patent‐style referential terms (e.g. “thereof,” “same,” “herein”).

    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
     Мы
    -2.11
     сцен
    -1.84
    ➀
    -1.80
     commerciales
    -1.76
    さぁ
    -1.74
    低声
    -1.71
    蹑
    -1.71
    螣
    -1.67
     BEHAV
    -1.67
    簓
    -1.66
    POSITIVE LOGITS
     It
    2.45
     they
    2.05
     muerta
    1.87
    ми
    1.80
    ll
    1.77
    1
    1.77
    už
    1.77
    følgelig
    1.77
    0
    1.71
    としては
    1.69
    Activations Density 0.020%

    No Known Activations