© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48981
    Prev
    Next
    INDEX
    Explanations

    interjection followed by "it"

    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/layer_40_width_65k_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
    表
    0.38
    ogen
    0.37
    five
    0.37
    Guj
    0.37
     кеңселер
    0.36
     Angst
    0.36
    threading
    0.36
    满
    0.36
     halfway
    0.35
    ambahkan
    0.35
    POSITIVE LOGITS
     ní
    0.39
     टाइगर
    0.38
     значит
    0.37
     继续
    0.36
     चर
    0.36
     ncols
    0.36
     sabot
    0.35
     analyt
    0.35
     ஆன்
    0.35
     kỹ
    0.34
    Activations Density 0.000%

    No Known Activations