© 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. 87396
    Prev
    Next
    INDEX
    Explanations

    secret operations or entities

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

    The neuron activates on the word “secret” (and its close derivatives like “secretly”) anywhere it appears.

    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
                
    -1.98
     میتوان
    -1.86
     persuaded
    -1.85
     to
    -1.77
     когато
    -1.77
     glaub
    -1.75
     gefährlich
    -1.75
    第一章
    -1.74
    很棒
    -1.71
    (
    -1.71
    POSITIVE LOGITS
    t
    1.91
    Второй
    1.84
    Поэтому
    1.84
     Exactly
    1.82
    ENT
    1.81
    Они
    1.80
    艿
    1.71
     دارید
    1.70
    ist
    1.69
    谨慎
    1.69
    Activations Density 0.013%

    No Known Activations