© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 48346
    Prev
    Next
    INDEX
    Explanations

    return or none after code blocks

    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
    顺利
    0.44
     lice
    0.41
     pantalla
    0.40
     progreso
    0.39
     विनो
    0.39
    杞
    0.38
     processing
    0.38
     permitir
    0.38
    غیر
    0.38
     await
    0.37
    POSITIVE LOGITS
     расс
    0.36
     কর্মক
    0.35
    ज्यो
    0.35
    みんな
    0.35
    
    0.34
     ಸದಸ್ಯ
    0.34
    শ্ব
    0.33
    straße
    0.33
    hores
    0.32
     setToDefault
    0.32
    Activations Density 0.114%

    No Known Activations