© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    novel biography

    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
     Developmental
    0.46
     systemic
    0.44
     psychiatric
    0.41
    
    0.41
     solubility
    0.40
     ethylene
    0.40
     competency
    0.40
     subcutaneous
    0.40
    医药
    0.40
     developmental
    0.40
    POSITIVE LOGITS
     가
    0.52
     échelle
    0.51
     izdel
    0.50
     מ
    0.49
     επι
    0.49
     ép
    0.48
    avatt
    0.48
     Kingdoms
    0.48
    iyet
    0.48
    妑
    0.48
    Activations Density 0.005%

    No Known Activations