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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83685
    Prev
    Next
    INDEX
    Explanations

    such that

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

    The neuron activates on occurrences of the word “such” (often in the “such that” construction).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    CONCLUS
    -0.88
     Erit
    -0.83
    ⾞
    -0.83
    য়া
    -0.82
    カンド
    -0.81
     الأربع
    -0.81
    Junction
    -0.79
     Zü
    -0.78
     impos
    -0.77
    Laugh
    -0.77
    POSITIVE LOGITS
     that
    2.69
     as
    1.15
     latter
    0.93
     even
    0.90
     garaje
    0.86
    ligently
    0.85
     vielfäl
    0.84
     kinds
    0.82
     hemsida
    0.82
     که
    0.81
    Activations Density 0.027%

    No Known Activations