© 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. 4505
    Prev
    Next
    INDEX
    Explanations

    Do you want

    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
     waitress
    0.79
    ႇ
    0.77
    strated
    0.77
     Roshelle
    0.75
     embod
    0.75
    kloud
    0.74
    lesque
    0.74
    iolipin
    0.72
    liquer
    0.72
     ascertain
    0.71
    POSITIVE LOGITS
    M
    0.76
     Hause
    0.75
    D
    0.69
     معا
    0.66
     cốt
    0.65
     Dort
    0.65
     سالم
    0.63
    σε
    0.63
    T
    0.62
     erwartet
    0.62
    Activations Density 0.021%

    No Known Activations