© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    Names of people

    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
    2
    0.58
    0.54
      
    0.53
    s
    0.53
    ie
    0.51
    1
    0.51
    ly
    0.51
     +
    0.51
    y
    0.51
    ged
    0.50
    POSITIVE LOGITS
    arrerol
    0.89
    chyné
    0.81
    addena
    0.77
    ayvachi
    0.76
    Concini
    0.75
    ómago
    0.74
     previewBuilder
    0.74
    暊
    0.73
    BUGFS
    0.73
    Bechyné
    0.73
    Activations Density 0.050%

    No Known Activations