© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    links to articles and answers

    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
     Green
    0.67
    Green
    0.66
    ique
    0.64
     laisser
    0.63
     ترك
    0.60
     GREEN
    0.60
    gre
    0.60
    绿
    0.59
     Greens
    0.59
    ysm
    0.59
    POSITIVE LOGITS
    沙发
    0.66
    canoe
    0.65
     spreadsheets
    0.65
     spreadsheet
    0.61
    σό
    0.57
     ரே
    0.57
     endanger
    0.57
     endangered
    0.56
    ut
    0.56
    ্যাড
    0.56
    Activations Density 0.202%

    No Known Activations