© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2052
    Prev
    Next
    INDEX
    Explanations

    billion years

    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
    Negative Logits
    सुबह
    0.70
    MOND
    0.65
    শুক্র
    0.64
    ουσ
    0.63
     утром
    0.60
    itzel
    0.59
    Monday
    0.59
     интерфей
    0.58
    籵
    0.58
    Weekly
    0.57
    POSITIVE LOGITS
     year
    5.69
     years
    5.27
    year
    5.25
    Year
    5.14
     Year
    5.04
    years
    4.75
     Years
    4.68
     YEAR
    4.65
    Years
    4.62
    YEAR
    4.55
    Activations Density 0.698%

    No Known Activations