© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10228
    Prev
    Next
    INDEX
    Explanations

    introduction timing markers

    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_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
    都沒有
    0.80
    fields
    0.78
    ologici
    0.75
    admin
    0.75
    status
    0.73
    жами
    0.72
    ᅨ
    0.72
     처
    0.72
    ambiente
    0.70
    arten
    0.69
    POSITIVE LOGITS
    Задача
    0.90
     Задача
    0.85
     Largest
    0.81
     speaking
    0.81
     largest
    0.80
     sworn
    0.78
     Lleg
    0.77
     grim
    0.75
     час
    0.74
     Speaking
    0.74
    Activations Density 0.010%

    No Known Activations