© 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. 4803
    Prev
    Next
    INDEX
    Explanations

    /us/ links

    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
     Ital
    0.75
    extré
    0.73
    niku
    0.73
     Melville
    0.70
    <ul>
    0.69
    বাল
    0.69
     thiện
    0.67
     Ré
    0.66
     repel
    0.64
     lleva
    0.64
    POSITIVE LOGITS
    again
    0.69
     assuring
    0.62
     reassuring
    0.61
    optical
    0.61
    毬
    0.60
     optical
    0.60
     metamorphosis
    0.60
     सदा
    0.59
     syrup
    0.58
    хи
    0.58
    Activations Density 0.111%

    No Known Activations