© 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. 22-GEMMASCOPE-RES-131K
    7. 70835
    Prev
    Next
    INDEX
    Explanations

    removing or stopping an action

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

    The neuron fires on words that signal removal or deletion actions (e.g. delete, remove, uninstall).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     spelar
    -0.89
     της
    -0.88
     Heim
    -0.86
    LJ
    -0.84
    抜け
    -0.84
     on
    -0.84
     dealloc
    -0.84
    ္
    -0.83
    始めた
    -0.81
     Quell
    -0.80
    POSITIVE LOGITS
     and
    1.55
     then
    1.32
     old
    1.29
     puis
    1.25
     huidige
    1.13
    แล้ว
    1.12
    然后
    1.09
     previous
    1.09
     replaced
    1.04
    Then
    1.02
    Activations Density 0.060%

    No Known Activations