© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1639
    Prev
    Next
    INDEX
    Explanations

    subject followed by "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     состоит
    0.86
    ებულია
    0.71
    的就是
    0.70
     is
    0.69
     liegt
    0.68
     zorgt
    0.67
     geeft
    0.66
    "][
    0.66
     заключается
    0.66
    ोज़
    0.65
    POSITIVE LOGITS
     to
    1.41
     να
    1.39
    ToBe
    1.29
     להיות
    1.25
     ausz
    1.09
    to
    1.08
     einz
    1.03
     להת
    1.03
     să
    1.00
     abz
    0.97
    Activations Density 0.214%

    No Known Activations