© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2992
    Prev
    Next
    INDEX
    Explanations

    keywords followed by lists

    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_13_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
     ($\
    0.97
    groupby
    0.88
    อังกฤษ
    0.86
    etum
    0.84
    tego
    0.84
    िश्व
    0.84
    ıldı
    0.83
    스로
    0.82
     (${
    0.82
     sinnv
    0.82
    POSITIVE LOGITS
    That
    1.02
     Memorandum
    0.99
    ‌هایی
    0.89
    Now
    0.88
     Have
    0.88
    How
    0.86
     That
    0.85
    Concluding
    0.83
     concluded
    0.82
     How
    0.82
    Activations Density 0.349%

    No Known Activations