© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 87
    Prev
    Next
    INDEX
    Explanations

    Java class constructs

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

    programming code snippets

    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
    廡
    0.54
    礬
    0.48
    蟎
    0.45
     реки
    0.44
    幄
    0.43
    餛
    0.43
    తున్నాయి
    0.42
     VESSELS
    0.42
    鯢
    0.42
     SIINFEKL
    0.42
    POSITIVE LOGITS
    Builder
    0.75
    ::
    0.75
     extends
    0.73
    Manager
    0.73
    Factory
    0.72
    Impl
    0.71
    <?>
    0.70
    <
    0.70
     class
    0.70
    Exception
    0.69
    Activations Density 0.031%

    No Known Activations