© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13710
    Prev
    Next
    INDEX
    Explanations

    Republic Day

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    dik
    0.69
    Dik
    0.66
     Dik
    0.64
    癸
    0.60
    ட்டம்
    0.57
    dzi
    0.56
    Abraham
    0.55
    荚
    0.54
    вай
    0.54
    ុម
    0.54
    POSITIVE LOGITS
     bru
    0.56
     ling
    0.55
     mediation
    0.55
     dressing
    0.54
     dressings
    0.54
     college
    0.54
     KNOW
    0.54
     لين
    0.54
     hearing
    0.54
     معرف
    0.53
    Activations Density 0.000%

    No Known Activations