© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    words with common suffixes

    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
     approaches
    0.67
     approach
    0.62
    https
    0.61
    প্রকাশ
    0.56
     contraire
    0.56
    otic
    0.55
     should
    0.54
    险
    0.54
     চিকিত
    0.53
    每年
    0.53
    POSITIVE LOGITS
    ării
    0.93
    вого
    0.91
    ului
    0.90
    чного
    0.88
    тического
    0.86
    ного
    0.86
    ného
    0.86
    ého
    0.84
    щего
    0.83
    ového
    0.82
    Activations Density 0.206%

    No Known Activations