© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    remove the flag

    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
    껭
    0.44
    kovskij
    0.40
     ionized
    0.39
     hydrogenation
    0.39
     antiguos
    0.38
     नाखून
    0.38
    không
    0.38
    ㏄
    0.38
    碗
    0.37
    ńska
    0.37
    POSITIVE LOGITS
     تحد
    0.50
     Entity
    0.48
     Entities
    0.41
     بحث
    0.40
     ظل
    0.40
     Meteorological
    0.40
     Editar
    0.39
     تساعد
    0.39
     few
    0.38
     entity
    0.38
    Activations Density 0.000%

    No Known Activations