© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    exceeding limits or thresholds

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

    surpass or exceed

    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
    ить
    0.38
    祜
    0.37
     değişik
    0.36
    ジェクト
    0.35
    哴
    0.35
     itibaren
    0.35
     क्लिक
    0.35
    烀
    0.34
    னம்
    0.34
     हेम
    0.34
    POSITIVE LOGITS
     surpass
    3.39
     surpassed
    3.25
     surpasses
    3.20
     exceed
    3.08
     exceeded
    3.03
     surpassing
    3.03
     exceeds
    3.02
     превы
    2.66
     vượt
    2.66
     exceeding
    2.58
    Activations Density 0.248%

    No Known Activations