© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    named institutions and organizations

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

    National followed by support service types

    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
    𝑏
    0.32
    yntax
    0.29
     ALU
    0.29
     Rasp
    0.28
     DecodingError
    0.28
    蝴
    0.28
    部门
    0.27
     Departamento
    0.27
    微软雅黑
    0.27
    bewerken
    0.27
    POSITIVE LOGITS
     Veterinary
    0.28
    ста
    0.28
     Agricultural
    0.26
     liberd
    0.25
     Agricult
    0.24
    ти
    0.24
    сово
    0.24
    servic
    0.24
    ᆫ
    0.24
    fod
    0.24
    Activations Density 0.216%

    No Known Activations