© 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. 3158
    Prev
    Next
    INDEX
    Explanations

    programming arguments and events

    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
     Situ
    0.79
    .$\
    0.77
     Слу
    0.77
     Mean
    0.77
     DOI
    0.76
     MEAN
    0.76
     Symbol
    0.75
     glLight
    0.73
     상
    0.73
     CUDA
    0.73
    POSITIVE LOGITS
    args
    1.51
    arg
    1.37
    obj
    1.24
    data
    1.20
     args
    1.19
    input
    1.17
    target
    1.14
     _)
    1.12
    params
    1.12
    event
    1.10
    Activations Density 0.205%

    No Known Activations