© 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. 124615
    Prev
    Next
    INDEX
    Explanations

    stand with prepositions

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

    The neuron fires on different forms of the verb “stand” (e.g. stand, standing, stands, stonde).

    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
    www
    -1.95
    1
    -1.90
    6
    -1.80
     Two
    -1.76
     النها
    -1.75
    끽
    -1.75
     Outros
    -1.73
     quartet
    -1.72
    ﮟ
    -1.72
    .
    -1.71
    POSITIVE LOGITS
    ”;
    2.58
    ”,
    2.53
    ”:
    2.48
    ).”
    2.33
    ?”
    2.28
    !”
    2.25
    ”)
    2.22
    ),”
    2.11
     empfiehlt
    2.09
    ";
    2.06
    Activations Density 0.028%

    No Known Activations