© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4092
    Prev
    Next
    INDEX
    Explanations

    button and translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ляти
    0.42
    FDA
    0.42
    对象的
    0.41
    Persona
    0.41
    кина
    0.41
    オブジェクト
    0.40
    ፐ
    0.40
    讽
    0.39
     طور
    0.39
     способности
    0.39
    POSITIVE LOGITS
     button
    0.86
     buttons
    0.78
     Button
    0.72
    按钮
    0.72
     btn
    0.67
     버튼
    0.67
    button
    0.66
     botón
    0.66
     кнопку
    0.66
     resetButton
    0.66
    Activations Density 0.186%

    No Known Activations