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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67621
    Prev
    Next
    INDEX
    Explanations

    what it means

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

    The neuron fires on occurrences of the word “means,” especially in explanatory or definitional contexts.

    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
    𖧵
    -2.22
     résine
    -2.13
    鵙
    -2.11
     étan
    -2.09
     verdaderos
    -2.09
     faciliter
    -2.02
     acrylique
    -2.00
     utilisant
    -1.98
    wasn
    -1.97
    ఽ
    -1.95
    POSITIVE LOGITS
     for
    2.73
     from
    2.22
     to
    2.11
     they
    2.09
     through
    2.05
     of
    2.05
     Our
    1.96
     about
    1.91
     on
    1.89
     began
    1.82
    Activations Density 0.006%

    No Known Activations