© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4505
    Prev
    Next
    INDEX
    Explanations

    diy, hobby, homemade

    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
    iseconds
    0.79
    函数的
    0.75
     वर्त
    0.73
     agencia
    0.72
     khớp
    0.72
    ologo
    0.72
    စ္
    0.72
     މ
    0.72
    баты
    0.71
     اجلاس
    0.70
    POSITIVE LOGITS
     DIY
    2.73
    DIY
    2.59
     diy
    2.03
    diy
    1.99
     hobby
    1.86
     homemade
    1.76
     Homemade
    1.64
    hobby
    1.59
    Homemade
    1.57
     amateur
    1.52
    Activations Density 0.796%

    No Known Activations