© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    bruise

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

    pythonOlá

    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
    Linki
    0.41
    ooky
    0.40
    agonia
    0.40
     зи
    0.39
    outed
    0.39
    жих
    0.39
    oxine
    0.39
    暗
    0.38
    सीबी
    0.38
    ミ
    0.38
    POSITIVE LOGITS
     bruise
    0.59
     Bru
    0.55
     bruised
    0.55
     bruises
    0.52
     bru
    0.50
    Bru
    0.47
    bru
    0.46
     chilled
    0.45
     bruising
    0.45
     Bruins
    0.44
    Activations Density 0.000%

    No Known Activations