© 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. 34-GEMMASCOPE-RES-131K
    7. 109727
    Prev
    Next
    INDEX
    Explanations

    out and direction

    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_34/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
    čnost
    -0.84
    ocats
    -0.83
    เริ่ม
    -0.83
    Подроб
    -0.81
     használ
    -0.79
    來了
    -0.78
    ùn
    -0.78
    camisas
    -0.78
    選択肢
    -0.77
     geschikt
    -0.77
    POSITIVE LOGITS
     onto
    2.27
     out
    1.95
     выходит
    1.45
     выхода
    1.23
     directly
    1.20
     вышла
    1.20
     вышел
    1.17
    onto
    1.13
    出去
    1.13
    ออก
    1.13
    Activations Density 0.018%

    No Known Activations