© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5601
    Prev
    Next
    INDEX
    Explanations

    legal entity

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

    Named entities

    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_53_width_65k_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
     tcpHeader
    0.44
     كأس
    0.41
     وکړئ
    0.41
     pInBuffer
    0.40
     кварта
    0.40
     Apostolic
    0.39
    ParameterActive
    0.38
    溪
    0.38
    カフェ
    0.38
     புக
    0.38
    POSITIVE LOGITS
     entity
    4.25
     Entity
    4.09
    Entity
    3.91
    entity
    3.88
     entities
    3.88
     Entities
    3.80
    entities
    3.52
    实体
    3.52
     entidade
    3.48
    Entities
    3.47
    Activations Density 0.067%

    No Known Activations