© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11782
    Prev
    Next
    INDEX
    Explanations

    words ending in ar or containing ar

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

    modularity and suffixes

    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
    դ
    0.54
    ますが
    0.50
    ي
    0.49
    În
    0.47
    ીર
    0.44
    կ
    0.43
    )【
    0.43
    ت
    0.43
    ე
    0.42
    Ε
    0.42
    POSITIVE LOGITS
    beitet
    0.59
    beiten
    0.57
    ্সের
    0.56
    িত্ব
    0.55
    riors
    0.55
    iposa
    0.54
    riage
    0.52
    ithmetic
    0.52
    ınız
    0.52
    beitung
    0.50
    Activations Density 0.941%

    No Known Activations