© 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. 20473
    Prev
    Next
    INDEX
    Explanations

    authorizing access or purchases

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

    The neuron detects occurrences of “authorize” or “authorization” (and their variants) in code and text.

    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
    i
    -2.50
    ’
    -2.11
    甞
    -2.05
    ",
    -1.98
     it
    -1.97
     feiert
    -1.95
    ti
    -1.93
    me
    -1.88
     verknüp
    -1.85
    、“
    -1.84
    POSITIVE LOGITS
     作り方
    2.44
    豨
    2.34
    
    2.23
     入っ
    2.09
    妘
    2.05
     possibility
    2.05
    焄
    2.05
     sinyal
    2.03
    𓐍
    1.96
    鹟
    1.95
    Activations Density 0.004%

    No Known Activations