© 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. 22-GEMMASCOPE-RES-131K
    4. 104355
    Prev
    Next
    INDEX
    Explanations

    Neither...nor, permission

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

    This neuron identifies the clause in software licenses that forbids using the copyright holder’s name in advertising or publicity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    }`)
    -1.13
     inuti
    -1.05
     Ouv
    -1.04
     parlament
    -0.99
    ]').
    -0.96
    )){
    -0.90
    ]")
    -0.89
    ')){
    -0.89
    ")));
    
    -0.88
    ));
    
    -0.87
    POSITIVE LOGITS
     грамм
    1.10
    ַל
    1.05
    Neither
    1.05
     memutus
    0.97
     forbidden
    0.95
    擰
    0.95
    也不會
    0.95
     Neither
    0.95
    спользование
    0.94
     soutenir
    0.94
    Activations Density 0.067%

    No Known Activations