© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 55981
    Prev
    Next
    INDEX
    Explanations

    starters, fireworks, fish, detection

    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
     дерев
    0.44
    ர்களையும்
    0.44
    湖
    0.42
     contador
    0.42
    ཥ
    0.42
     множе
    0.41
    에도
    0.40
     космо
    0.40
     кот
    0.40
     FINANCE
    0.40
    POSITIVE LOGITS
     આવા
    0.44
     proteolytic
    0.44
     Type
    0.43
    的
    0.41
     insecticide
    0.41
    utilizzo
    0.41
     Peltier
    0.40
     Kombat
    0.40
     Studien
    0.40
    ㅤ
    0.40
    Activations Density 0.006%

    No Known Activations