© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67724
    Prev
    Next
    INDEX
    Explanations

    phrases starting with In, Q:, March

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

    This neuron activates on LaTeX table/array column‐format specifiers (e.g. the “l” in an `{array}{l}` alignment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ݀
    -1.42
    どのような
    -1.35
    オススメ
    -1.27
    壜
    -1.26
    もうすぐ
    -1.26
     various
    -1.25
     verschill
    -1.24
     cultuur
    -1.23
    鹀
    -1.21
     truco
    -1.20
    POSITIVE LOGITS
    !
    1.80
    /
    1.27
    y
    1.27
    **
    1.23
    o
    1.22
    z
    1.20
     precisam
    1.19
    都是
    1.19
    ha
    1.17
    .'
    1.17
    Activations Density 0.000%

    No Known Activations