© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2577
    Prev
    Next
    INDEX
    Explanations

    code followed by parentheses

    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_17_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
    imee
    0.84
    坭
    0.78
     Martine
    0.77
    ्राष्ट
    0.73
    স্তে
    0.72
    <0x97>
    0.72
    苖
    0.71
    jos
    0.70
    নাই
    0.70
     Shyam
    0.70
    POSITIVE LOGITS
     "(
    0.93
    "(
    0.77
     Sichuan
    0.76
     nerfs
    0.75
     panel
    0.75
     Parker
    0.75
     $(
    0.74
     parentheses
    0.74
    [(
    0.73
     irritation
    0.73
    Activations Density 0.199%

    No Known Activations