© 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. 34-GEMMASCOPE-RES-131K
    7. 50112
    Prev
    Next
    INDEX
    Explanations

    seeking or granting permission

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

    The neuron fires on words and phrases that grant or reference permission or licensing rights (e.g., giving permission, license terms, special exceptions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    czej
    -0.73
    nungs
    -0.72
     paillettes
    -0.71
     profiter
    -0.71
    Ẳ
    -0.70
    ตู
    -0.67
     PLATE
    -0.66
    vore
    -0.66
     prestig
    -0.66
    Morfologia
    -0.65
    POSITIVE LOGITS
     permission
    7.59
    permission
    5.69
     Permission
    5.53
    Permission
    5.22
     permissions
    4.78
     permiso
    4.06
     authorization
    4.06
     approval
    4.00
    PERMISSION
    4.00
     consent
    3.88
    Activations Density 0.148%

    No Known Activations