© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27086
    Prev
    Next
    INDEX
    Explanations

    SOP CL TC

    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
    》。
    0.50
    append
    0.45
    
    0.42
    Ҭ
    0.42
    default
    0.42
     angegeben
    0.41
    
    0.41
    
    0.41
    final
    0.40
    الصفحه
    0.40
    POSITIVE LOGITS
     ঘৃ
    0.45
    âl
    0.42
    zocht
    0.39
     gà
    0.39
    uj
    0.39
     hå
    0.39
     උ
    0.38
     eel
    0.38
    alin
    0.38
     nl
    0.38
    Activations Density 0.002%

    No Known Activations