© 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. 790
    Prev
    Next
    INDEX
    Explanations

    list item 2

    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
    ↵
    0.80
     cup
    0.65
    glyphicon
    0.64
    ”,
    0.63
    <0xB4>
    0.61
    }`,
    0.61
     záv
    0.61
    毂
    0.59
    setwd
    0.59
    )}_{
    0.57
    POSITIVE LOGITS
    2
    1.54
    ２
    1.12
    २
    1.04
    ២
    1.00
    ๒
    0.96
    ❷
    0.94
    ૨
    0.94
    二
    0.93
    ᱒
    0.90
     ២
    0.90
    Activations Density 1.174%

    No Known Activations