© 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-262K
    7. 123998
    Prev
    Next
    INDEX
    Explanations

    speaking fluently, checking, accuracy

    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_262k_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
     literals
    0.45
     pointwise
    0.44
    
    0.41
     (`
    0.41
     #(
    0.41
     ([]
    0.41
     Viewed
    0.40
     Bytes
    0.40
     Bigger
    0.40
     সেপ্ট
    0.40
    POSITIVE LOGITS
    isotope
    0.50
    兕
    0.50
    oglobin
    0.47
     quinine
    0.46
    projectile
    0.46
     aureus
    0.45
     insulin
    0.45
    ebilir
    0.43
    各类
    0.43
     hospital
    0.43
    Activations Density 0.001%

    No Known Activations