© 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. 8015
    Prev
    Next
    INDEX
    Explanations

    p endings

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

    VP, Imps, rasp, lerp, PvP

    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
    illées
    0.44
     Packages
    0.42
    ів
    0.40
    的点
    0.40
    𝒸
    0.40
    껐
    0.40
     पब्लिक
    0.39
    頪
    0.38
    鍖
    0.38
     Premises
    0.38
    POSITIVE LOGITS
    p
    1.89
    ps
    1.71
    ｐ
    1.70
    پ
    1.60
    pe
    1.50
    ping
    1.48
    pp
    1.43
    ਪ
    1.43
    প
    1.41
    п
    1.41
    Activations Density 0.125%

    No Known Activations