© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57034
    Prev
    Next
    INDEX
    Explanations

    just, only, simply, merely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    uj
    0.39
    correcto
    0.39
     باید
    0.38
    asti
    0.38
    ille
    0.38
    aus
    0.38
    ལ་
    0.37
     «
    0.37
     agak
    0.37
     terrible
    0.36
    POSITIVE LOGITS
     merely
    1.33
    只是
    1.29
     only
    1.10
     simply
    1.08
     лишь
    1.05
     просто
    1.05
     فقط
    1.05
    只会
    1.05
     sadece
    1.03
     только
    1.00
    Activations Density 0.000%

    No Known Activations