© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86898
    Prev
    Next
    INDEX
    Explanations

    any person obtaining

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

    The neuron specializes in spotting the permissive‐license “permission grant” language—phrases about “any person obtaining a copy…to use, copy, modify, merge, distribute, etc.”

    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
    前世
    -0.68
    isShowing
    -0.68
    mení
    -0.66
     Boyce
    -0.64
    函
    -0.63
     Quests
    -0.60
    uels
    -0.59
     Grosso
    -0.58
     Alexand
    -0.57
    珲
    -0.57
    POSITIVE LOGITS
    PHO
    0.73
    trial
    0.69
    ρε
    0.69
     文化
    0.69
     FIVE
    0.69
    Trial
    0.68
     برق
    0.68
     WEE
    0.68
    bread
    0.67
    five
    0.66
    Activations Density 0.094%

    No Known Activations