© 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
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    Psychology Today Health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disturbs
    0.70
    ęcia
    0.69
     #${
    0.69
     Toolbar
    0.66
     Song
    0.63
     revolver
    0.61
    ចប់
    0.61
     সমু
    0.61
    ∈</
    0.60
     Lösungen
    0.60
    POSITIVE LOGITS
    Health
    0.71
    DIRECTORY
    0.69
    Hallo
    0.67
     vitamins
    0.66
    health
    0.66
    Worker
    0.63
    行
    0.62
    천
    0.62
     health
    0.62
     vitamin
    0.62
    Activations Density 0.201%

    No Known Activations