© 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. 7554
    Prev
    Next
    INDEX
    Explanations

    Int words

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

    Int words

    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
    致
    0.39
    なん
    0.38
    覽
    0.38
    아요
    0.37
     menyer
    0.37
    鄙
    0.37
    览
    0.36
    čit
    0.36
    лете
    0.36
    ^{+}\
    0.36
    POSITIVE LOGITS
    rinsic
    0.77
    estinal
    0.76
     Int
    0.74
     intra
    0.71
     Intra
    0.70
    Int
    0.70
    entionally
    0.69
     intras
    0.67
    elligent
    0.66
    uitively
    0.64
    Activations Density 0.031%

    No Known Activations