© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_262k_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
    _:
    0.89
    _
    0.79
     _:
    0.74
    ：
    0.72
    ２
    0.69
    其次
    0.68
    PLIED
    0.66
     dalej
    0.65
    ls
    0.64
    ｊ
    0.63
    POSITIVE LOGITS
     =
    0.97
     =(
    0.90
     =[
    0.87
     $=$
    0.85
     $=\
    0.83
     ={
    0.82
     Create
    0.82
     =,
    0.80
     Generate
    0.79
    $=\
    0.78
    Activations Density 0.038%

    No Known Activations