© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    unified, united, or unifying

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

    unity and unification

    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
    閬
    0.47
     intermittent
    0.43
     الرخصة
    0.42
    ldecode
    0.40
     dérou
    0.38
    夭
    0.38
    Permissions
    0.36
    
    0.35
     intermittently
    0.35
     intermitt
    0.35
    POSITIVE LOGITS
     unity
    3.64
     unified
    3.58
     unify
    3.38
     unifying
    3.34
     unification
    3.31
    unified
    3.27
     unite
    3.25
     united
    3.23
     Unity
    3.14
     uniting
    3.14
    Activations Density 0.184%

    No Known Activations