© 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. 48908
    Prev
    Next
    INDEX
    Explanations

    technical definitions and structures

    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
    楽天
    0.46
    oluene
    0.43
    usión
    0.43
     करण्यासाठी
    0.43
     נישט
    0.42
     نکن
    0.42
    лександр
    0.42
    с
    0.42
    analyse
    0.42
    akty
    0.41
    POSITIVE LOGITS
     Architecture
    0.52
     Development
    0.51
     École
    0.50
     Studio
    0.50
     Implementation
    0.49
     Holds
    0.47
     curricula
    0.47
     Ivy
    0.46
     Concrete
    0.46
     Engineering
    0.46
    Activations Density 0.002%

    No Known Activations