© 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. 41960
    Prev
    Next
    INDEX
    Explanations

    disabling specific things

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

    The neuron is triggered by the occurrence of the token “disable.”

    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
     
    -3.36
    ?
    -3.33
    ↵↵
    -3.22
    '
    -3.20
    _
    -2.75
     {
    -2.56
     حتى
    -2.48
            
    -2.48
    *
    -2.48
    –
    -2.45
    POSITIVE LOGITS
    澌
    3.41
    谵
    2.63
    涑
    2.61
    了一个
    2.56
     сист
    2.55
    潆
    2.53
    ጺ
    2.52
    ‪.‬‬
    2.48
    瘓
    2.48
    Ꮴ
    2.47
    Activations Density 0.008%

    No Known Activations