© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 784
    Prev
    Next
    INDEX
    Explanations

    greetings and good sentiments in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    驺
    -2.64
     prachtige
    -2.53
    跸
    -2.48
    龅
    -2.45
    拶
    -2.44
    樒
    -2.41
    罴
    -2.41
    ৄ
    -2.36
     galeri
    -2.33
    晢
    -2.33
    POSITIVE LOGITS
    出て
    2.16
    ا
    2.08
    .”
    2.06
    」
    2.05
    This
    2.02
     Regardless
    1.97
    will
    1.95
    あります
    1.94
    Also
    1.92
    瓩
    1.91
    Activations Density 0.011%

    No Known Activations