© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    numbers and arrays

    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
     eller
    1.21
     Atau
    1.20
    或者
    1.16
     oder
    1.06
     atau
    1.05
    或是
    1.03
     یا
    1.03
    或
    1.03
     veya
    1.01
     ou
    1.01
    POSITIVE LOGITS
     primarily
    0.75
     mainly
    0.74
     consisting
    0.68
    における
    0.67
     இவரது
    0.66
     umožňuje
    0.64
     В
    0.64
     বিষয়ক
    0.64
     namely
    0.63
    mainly
    0.62
    Activations Density 0.464%

    No Known Activations