© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5162
    Prev
    Next
    INDEX
    Explanations

    shell commands and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     sui
    0.88
     helps
    0.87
     is
    0.86
    ↵
    0.85
     sores
    0.79
    込
    0.76
     rejoin
    0.75
     key
    0.75
     serves
    0.75
     encourages
    0.75
    POSITIVE LOGITS
    Celebr
    1.06
    Hình
    0.94
    Creating
    0.90
    Able
    0.90
    Drew
    0.88
    asana
    0.87
    놈
    0.85
    developing
    0.85
    preparing
    0.84
    lar
    0.84
    Activations Density 0.028%

    No Known Activations