© 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. 17-GEMMASCOPE-2-RES-16K
    7. 16022
    Prev
    Next
    INDEX
    Explanations

    "oh" and "ah" interjections

    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_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
     pulgadas
    2.11
    o
    2.08
     itibaren
    2.01
    েকের
    1.97
    elem
    1.96
    ている
    1.95
    ᴛ
    1.91
    ので
    1.87
    ه
    1.84
     distinta
    1.83
    POSITIVE LOGITS
    klahoma
    2.02
    ים
    1.87
    রা
    1.83
    assay
    1.72
    s
    1.69
    ್ಟ
    1.66
    ans
    1.64
    iterations
    1.62
    یه
    1.62
    oski
    1.61
    Activations Density 0.128%

    No Known Activations