© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    sudo apt, yum, dnf

    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
    収入
    0.63
    isie
    0.58
    cation
    0.57
    sustaining
    0.56
    Foundation
    0.56
    ༄
    0.56
     Ory
    0.56
    டுத்து
    0.55
     aligning
    0.55
     ///<
    0.54
    POSITIVE LOGITS
     shelves
    0.61
     يد
    0.61
     कैंड
    0.60
    <0x8B>
    0.60
    尔多
    0.60
    رک
    0.58
     bookshelves
    0.58
     আর্টি
    0.57
     ე
    0.57
     boards
    0.56
    Activations Density 0.177%

    No Known Activations