© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102457
    Prev
    Next
    INDEX
    Explanations

    occupied, taken, or busy

    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
    huriyet
    -1.13
     必要
    -1.13
     理由
    -1.10
    ⒉
    -1.10
     resultat
    -1.10
     背
    -1.09
     全体
    -1.06
    र्जा
    -1.05
    autogui
    -1.05
    GPT
    -1.03
    POSITIVE LOGITS
     this
    1.42
    Слайд
    1.26
    𖡼
    1.16
     ingenious
    1.14
     это
    1.14
    but
    1.13
     می‌شوند
    1.13
    Материал
    1.12
    کنون
    1.12
    Далее
    1.11
    Activations Density 0.052%

    No Known Activations