© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    variation and variations

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

    write commands

    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
    郁
    0.41
     রক্ষ
    0.40
    crossbow
    0.40
     sovereignty
    0.39
    粗
    0.39
    ルの
    0.38
    Adorable
    0.38
    竍
    0.38
    aughter
    0.38
     facultad
    0.37
    POSITIVE LOGITS
    Variation
    1.32
     variation
    1.31
     Variation
    1.30
    variation
    1.26
     variations
    1.25
     Variations
    1.19
     variación
    1.08
     Vary
    0.87
     вари
    0.87
     vary
    0.84
    Activations Density 0.009%

    No Known Activations