© 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. 3650
    Prev
    Next
    INDEX
    Explanations

    class/object instantiation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    =!
    0.67
    href
    0.65
     Depois
    0.65
     Entire
    0.65
    =%
    0.65
     yerine
    0.64
    َت
    0.64
    थन
    0.63
    ché
    0.63
    வய
    0.63
    POSITIVE LOGITS
    类
    1.20
    Manager
    1.12
    Factory
    1.09
    InitTypeDef
    1.09
    类的
    1.09
    Builder
    1.07
    Constants
    1.07
    クラス
    1.06
    Options
    1.04
    Model
    1.04
    Activations Density 0.421%

    No Known Activations