© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112874
    Prev
    Next
    INDEX
    Explanations

    medical education, finance, personal health, real estate

    np_acts-logits-general · gemini-2.5-flash-lite

    what are parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     restore
    0.52
    restore
    0.50
    сив
    0.48
    સ
    0.47
    ли
    0.47
     innovate
    0.46
     energized
    0.46
    у
    0.46
    锹
    0.46
    qual
    0.46
    POSITIVE LOGITS
     ਟ
    0.46
     досить
    0.44
     rDNA
    0.43
     ਦਾ
    0.43
     paheli
    0.42
    🏨
    0.42
     একথা
    0.41
     একাডেম
    0.41
    🌡
    0.41
     dissipation
    0.41
    Activations Density 0.000%

    No Known Activations