© 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. 75383
    Prev
    Next
    INDEX
    Explanations

    checking and unchecking options

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

    This neuron responds to mentions of checking or unchecking UI options (e.g. “check,” “uncheck,” “enable,” “tick”) in instructions.

    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
    Information
    -1.02
    balho
    -0.99
    Certified
    -0.98
    我們
    -0.97
    BACK
    -0.96
    因为
    -0.94
    MITTED
    -0.94
     שלנו
    -0.94
     отдель
    -0.94
    ̭
    -0.94
    POSITIVE LOGITS
     voorbij
    1.08
    いくつか
    1.08
     sais
    1.05
     guapos
    1.02
    了两
    1.02
     więc
    1.02
     "
    1.01
     exager
    1.01
     entiendo
    1.00
     jeżeli
    1.00
    Activations Density 0.017%

    No Known Activations