Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 272
    Prev
    Next
    INDEX
    Explanations

    words ending in n't

    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_16_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
    ेंगू
    0.64
    官员
    0.62
    煽
    0.60
     केल्यानंतर
    0.59
    担忧
    0.59
     reduz
    0.58
     niềm
    0.57
     benötigen
    0.57
    テナンス
    0.56
    ności
    0.55
    POSITIVE LOGITS
    k
    0.94
    p
    0.65
    ’
    0.64
    ות
    0.61
    ↵
    0.60
    ert
    0.60
     TIME
    0.59
     אות
    0.56
    kons
    0.56
    ก
    0.56
    Activations Density 0.001%

    No Known Activations