© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11327
    Prev
    Next
    INDEX
    Explanations

    superlative intensity markers

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

    intensifiers and descriptive adjectives

    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_40_width_16k_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
    üd
    0.42
     えっ
    0.42
     部分
    0.40
    acha
    0.40
     পাথ
    0.39
    DummyView
    0.38
     甲
    0.38
    hitth
    0.38
     rigs
    0.38
    𝒚
    0.37
    POSITIVE LOGITS
     للغاية
    1.03
    ‌ترین
    0.89
     ביותר
    0.88
    ที่สุด
    0.85
     banget
    0.85
    ísimo
    0.84
    ៗ
    0.81
    すぎる
    0.79
    បំផុត
    0.79
     جدا
    0.76
    Activations Density 0.080%

    No Known Activations