© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2271
    Prev
    Next
    INDEX
    Explanations

    specialized emergence areas

    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
     کردار
    0.62
    στά
    0.60
    अस
    0.58
    строй
    0.57
    Quote
    0.57
     Quotes
    0.57
    стройство
    0.55
    趄
    0.55
     इक्
    0.55
     kuruluş
    0.55
    POSITIVE LOGITS
     areas
    2.39
     area
    2.29
     Area
    2.11
     Areas
    2.11
    areas
    2.10
     áreas
    2.06
    Area
    2.06
    area
    2.05
     área
    2.01
     aree
    1.98
    Activations Density 1.885%

    No Known Activations