© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4370
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
     Semi
    0.75
     ))->
    0.74
    壩
    0.73
     à
    0.72
     Roundtable
    0.71
     riguard
    0.71
     cu
    0.68
     BI
    0.68
    trs
    0.68
     предметов
    0.67
    POSITIVE LOGITS
     several
    0.66
     여러
    0.65
     wakt
    0.65
     মুঠ
    0.64
    ீ
    0.64
    zeros
    0.64
    several
    0.62
    Several
    0.62
    Index
    0.62
     benzer
    0.61
    Activations Density 0.171%

    No Known Activations