© 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-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2586
    Prev
    Next
    INDEX
    Explanations

    critical thinking and skepticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     servicing
    0.79
     组件
    0.72
     renovación
    0.71
    틋
    0.71
     دستور
    0.69
     syrups
    0.67
     برش
    0.67
     imageName
    0.67
     масте
    0.66
    汁
    0.66
    POSITIVE LOGITS
     skeptic
    2.06
     skept
    2.03
     skeptical
    1.90
     debunk
    1.85
     sceptical
    1.80
     conspiracy
    1.78
     scept
    1.75
     atheist
    1.73
     pseudos
    1.73
     skepticism
    1.72
    Activations Density 0.720%

    No Known Activations