© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8988
    Prev
    Next
    INDEX
    Explanations

    tub / bath related words

    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_9_width_262k_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
    ᅱ
    2.65
    $=
    2.56
     kilowatt
    2.52
     sneak
    2.50
    儡
    2.49
    рка
    2.44
    clearInterval
    2.41
     tata
    2.36
    ő
    2.35
     hundred
    2.35
    POSITIVE LOGITS
    z
    3.29
    ມີ
    2.90
    sofar
    2.89
     ovoj
    2.80
    نا
    2.72
    一个
    2.71
     awaiting
    2.70
    %>%
    2.67
     ifelse
    2.64
     campaigned
    2.61
    Activations Density 0.018%

    No Known Activations