© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    Chinese programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     গোলাবার
    0.90
    folders
    0.90
    변
    0.89
     описы
    0.87
     மாவட்ட
    0.87
    Folders
    0.84
    dataSource
    0.84
    Representation
    0.83
    립
    0.83
    emat
    0.81
    POSITIVE LOGITS
     LUX
    0.96
     MINI
    0.92
     feiern
    0.86
     raiding
    0.86
     préalable
    0.85
     trabajos
    0.84
     mimpi
    0.84
     attaques
    0.84
     circumstantial
    0.83
     persönlich
    0.82
    Activations Density 0.063%

    No Known Activations