© 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. 39768
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions and sizes

    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
     꺼
    0.45
    <unused98>
    0.43
     الظ
    0.43
    <unused39>
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     evolved
    0.42
     Auburn
    0.41
    中村
    0.39
     Kuy
    0.39
     pukul
    0.38
    POSITIVE LOGITS
     Servicios
    0.42
    ὶ
    0.41
    webservices
    0.41
    しい
    0.41
     Favorites
    0.41
    糖尿
    0.41
    0.40
     ACTIVITIES
    0.40
     함수의
    0.40
     calculations
    0.40
    Activations Density 0.000%

    No Known Activations