© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48508
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages indicating likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    姊
    0.37
    ierge
    0.37
     grave
    0.36
     Coyote
    0.36
     bal
    0.35
     bereit
    0.35
    𝟐
    0.35
    SystemService
    0.35
    시스템
    0.34
     элект
    0.34
    POSITIVE LOGITS
    ꯌ
    0.40
     mayoría
    0.40
     большинства
    0.39
     тобто
    0.39
     majorité
    0.39
    Eppo
    0.39
     sepak
    0.38
     racionais
    0.38
     اکثریت
    0.38
     contenant
    0.37
    Activations Density 0.007%

    No Known Activations