© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4700
    Prev
    Next
    INDEX
    Explanations

    abstract base classes and bots

    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
     fearless
    0.95
    <unused473>
    0.94
     conspicuous
    0.92
    ">→</
    0.92
    ক্টো
    0.92
     currentPage
    0.91
     meno
    0.91
    popen
    0.91
    <unused494>
    0.90
     indeterminate
    0.90
    POSITIVE LOGITS
     think
    0.92
     Chant
    0.90
    সাথে
    0.90
     մ
    0.90
     America
    0.88
    soul
    0.85
    листы
    0.84
     provide
    0.84
     spread
    0.84
    יש
    0.84
    Activations Density 0.000%

    No Known Activations