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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11144
    Prev
    Next
    INDEX
    Explanations

    Microsoft Teams, performance series

    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
    іл
    0.52
    Якщо
    0.51
     показателей
    0.48
    充满
    0.47
    伥
    0.47
     Зараз
    0.47
     želite
    0.45
     діяльності
    0.45
    篑
    0.44
     нә
    0.44
    POSITIVE LOGITS
    bread
    0.45
     bread
    0.43
    وب
    0.39
    টিক
    0.39
    dogan
    0.39
     Constit
    0.39
     Ont
    0.38
     App
    0.38
     Bas
    0.38
     Easy
    0.38
    Activations Density 0.000%

    No Known Activations