© 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. 10-GEMMASCOPE-RES-131K
    7. 86711
    Prev
    Next
    INDEX
    Explanations

    specify or modify

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

    The neuron fires on programming‐documentation or code identifiers that are imperative action words (like “Specify” or “modify”) used to label configuration or update routines.

    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
     to
    -3.27
    borderSide
    -2.58
    ༀ
    -2.56
    OUTUBE
    -2.55
    箆
    -2.45
    abatic
    -2.42
     serán
    -2.41
    姈
    -2.41
    ikusbot
    -2.36
     pentru
    -2.31
    POSITIVE LOGITS
    1
    3.83
    -
    2.72
    there
    2.47
     véhicule
    2.42
    Sebagai
    2.36
    Setelah
    2.34
    It
    2.33
     jouet
    2.33
    因為
    2.27
    Tempat
    2.27
    Activations Density 0.031%

    No Known Activations