© 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. 56155
    Prev
    Next
    INDEX
    Explanations

    but contrast

    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
     ಅಭಿ
    0.48
     کھل
    0.46
     ಔಷಧ
    0.44
     ملتی
    0.44
    論
    0.43
     berarti
    0.42
    
    0.42
    tis
    0.42
     ಕಾನೂ
    0.42
    苹
    0.42
    POSITIVE LOGITS
    （
    0.50
     entre
    0.47
    Used
    0.46
     instantly
    0.44
     each
    0.43
     almost
    0.43
    гры
    0.43
     strip
    0.43
    Henderson
    0.43
     usado
    0.42
    Activations Density 0.013%

    No Known Activations