© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17300
    Prev
    Next
    INDEX
    Explanations

    entity/dto/payload structures

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

    java, kotlin, c# code

    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
     प्रसंस्करण
    0.50
     języ
    0.50
    治
    0.45
     BasicContainer
    0.43
    зуа
    0.42
    /**
    0.42
    isième
    0.42
    städ
    0.41
    可视化
    0.41
    ⸩
    0.40
    POSITIVE LOGITS
    entities
    0.62
     entities
    0.54
    dto
    0.54
    entity
    0.50
    entiti
    0.50
    payload
    0.49
     entity
    0.49
     dto
    0.48
    Dto
    0.47
    DTO
    0.47
    Activations Density 0.001%

    No Known Activations