© 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. 89714
    Prev
    Next
    INDEX
    Explanations

    assistance with access

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

    The neuron activates on occurrences of the word “with.”

    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
    因为他
    -1.39
     took
    -1.36
     cuando
    -1.32
     benefited
    -1.31
    遑
    -1.29
     они
    -1.28
     has
    -1.24
    ांकि
    -1.23
    &
    -1.23
    だが
    -1.23
    POSITIVE LOGITS
     regards
    2.94
     regard
    2.55
     the
    2.45
    regard
    1.88
    standing
    1.85
    Regarding
    1.54
     how
    1.50
    咳咳
    1.50
    regards
    1.49
    olding
    1.47
    Activations Density 0.051%

    No Known Activations