© 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. 32827
    Prev
    Next
    INDEX
    Explanations

    technical terms following common words

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

    The neuron consistently lights up on LaTeX‐style mathematical notation—especially parentheses and variable tuples (like “(k,l)”) inside math mode.

    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
     pérd
    -1.00
     TÉ
    -0.98
    ”]
    -0.96
    UNTE
    -0.95
     Xem
    -0.94
     FEM
    -0.92
     penser
    -0.91
    etched
    -0.89
     BRING
    -0.89
    pote
    -0.89
    POSITIVE LOGITS
     almost
    1.27
     strongly
    1.24
     with
    1.13
    ｇ
    1.12
     nearly
    1.11
     strong
    1.09
     if
    1.06
     any
    1.04
     at
    1.04
     essential
    1.02
    Activations Density 0.065%

    No Known Activations