© 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-16K
    7. 3854
    Prev
    Next
    INDEX
    Explanations

    passing parameters and arguments

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unresponsive
    0.74
     statistics
    0.65
    罫
    0.64
     biographies
    0.64
    fibr
    0.64
     futile
    0.63
     monks
    0.62
    餓
    0.61
    AccessException
    0.61
     резидент
    0.61
    POSITIVE LOGITS
     Parameters
    2.01
     parameters
    1.86
     params
    1.85
    params
    1.82
    Parameters
    1.82
     Params
    1.80
    parameters
    1.77
     parameter
    1.74
     Parameter
    1.73
     parámetros
    1.72
    Activations Density 0.586%

    No Known Activations