© 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. 130807
    Prev
    Next
    INDEX
    Explanations

    mathematics limits and names

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

    This neuron detects the occurrence of the substring “lim” (as in “lim,” “Lim,” “limiting,” etc.), i.e. tokens related to limits.

    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
     about
    -2.58
     “
    -2.47
     

    -2.45
     of
    -2.44
    parian
    -2.30
    
    -2.30
    “
    -2.23
    ↵↵
    -2.23
    .”
    -2.22
    .“
    -2.17
    POSITIVE LOGITS
    m
    3.23
    釓
    2.97
    埽
    2.94
    𓐍
    2.73
    the
    2.70
    橚
    2.70
    y
    2.66
    lim
    2.59
    媜
    2.58
    ców
    2.50
    Activations Density 0.007%

    No Known Activations