© 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-262K
    7. 1530
    Prev
    Next
    INDEX
    Explanations

    code variables obj, key

    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
    ኵ
    0.51
    <unused491>
    0.50
    니
    0.47
    டக்கலை
    0.46
     natureza
    0.46
     دول
    0.46
    TypeList
    0.46
     있으
    0.46
    {(-
    0.45
    encerramento
    0.45
    POSITIVE LOGITS
     nama
    0.58
     nombre
    0.56
     $
    0.54
     args
    0.53
     another
    0.52
     username
    0.51
    译
    0.51
     )
    0.51
     название
    0.50
    ılık
    0.50
    Activations Density 0.330%

    No Known Activations