© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2850
    Prev
    Next
    INDEX
    Explanations

    Arabic numerals

    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_29_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
     Tian
    0.68
    ⁤
    0.63
    ())+
    0.63
    🏛
    0.62
    ⟋
    0.62
     chatbots
    0.62
    🌄
    0.62
     Guang
    0.61
    ‑
    0.61
     extraordin
    0.61
    POSITIVE LOGITS
    q
    0.66
    ht
    0.63
    qa
    0.61
    pta
    0.60
    Z
    0.60
    xt
    0.59
    rt
    0.59
    W
    0.59
    X
    0.58
     العد
    0.58
    Activations Density 0.362%

    No Known Activations