© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8666
    Prev
    Next
    INDEX
    Explanations

    female names and grading

    np_acts-logits-general · gemini-2.5-flash-lite

    AI assistant capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    ↵↵↵↵
    0.43
    謀
    0.43
     Recommended
    0.42
    ↵↵
    0.42
    ↵↵↵↵↵↵↵
    0.42
     Dismiss
    0.41
    *
    0.41
    †
    0.41
    POSITIVE LOGITS
     Alyssa
    0.46
     Clara
    0.45
     Fiona
    0.45
     Evelyn
    0.45
     Mabel
    0.44
     Amanda
    0.43
     grading
    0.43
     Clio
    0.43
     grader
    0.43
     Virgil
    0.42
    Activations Density 0.000%

    No Known Activations