© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58554
    Prev
    Next
    INDEX
    Explanations

    without prejudice or limitation

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

    The neuron consistently fires on occurrences of permissive‐license grant language—especially the word “without” (as in “without restriction”) and related terms like “free of charge.”

    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
     nearly
    -0.92
     benefits
    -0.87
     probably
    -0.81
     really
    -0.80
    予想
    -0.79
     guidelines
    -0.78
     seemingly
    -0.77
    しないと
    -0.77
    uncios
    -0.77
     bumped
    -0.76
    POSITIVE LOGITS
     prejudice
    1.23
     '.$
    0.94
    
    0.94
     limitation
    0.93
     Prejudice
    0.91
     obligation
    0.91
    ORMAL
    0.89
     zza
    0.88
    fähig
    0.86
    möglichen
    0.85
    Activations Density 0.058%

    No Known Activations