© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 184
    Prev
    Next
    INDEX
    Explanations

    Orange, Oregon, organisational

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

    entity types or technical terms

    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
    出的
    0.46
    ֵ
    0.45
     xuất
    0.43
     itertools
    0.42
     välja
    0.40
     ए
    0.40
     Paralym
    0.40
     Vý
    0.39
    ቿ
    0.39
     fà
    0.39
    POSITIVE LOGITS
    ｵ
    1.45
     オ
    1.42
     О
    1.41
     오
    1.39
     ઓ
    1.35
     オー
    1.31
    オー
    1.26
     Ó
    1.25
     ኦ
    1.25
    О
    1.25
    Activations Density 0.606%

    No Known Activations