© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14506
    Prev
    Next
    INDEX
    Explanations

    websites, affiliate networks

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

    The neuron is picking up tokens typical of website footer disclaimers about ownership, rights, and official status (e.g. in “All materials on this site are the property of…”).

    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
     aptly
    -1.13
     When
    -1.13
     on
    -1.05
     has
    -0.99
     streamlined
    -0.98
     inexp
    -0.98
     epitom
    -0.98
     They
    -0.98
     According
    -0.97
     embell
    -0.97
    POSITIVE LOGITS
     billetes
    1.33
    えっ
    1.30
     movimentos
    1.22
     officielles
    1.18
    ビックリ
    1.16
     vehículos
    1.16
     véhicules
    1.16
     indivíduos
    1.15
     privées
    1.15
    んだよ
    1.14
    Activations Density 0.042%

    No Known Activations