© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    former/also/Elara

    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
     各
    0.49
     необхідно
    0.45
     എങ്ങനെ
    0.45
     ವೇಳ
    0.43
     लगेंगे
    0.43
     สิ่ง
    0.41
     система
    0.41
    તાવ
    0.41
     두
    0.41
     должны
    0.40
    POSITIVE LOGITS
    也是
    0.59
     ebenfalls
    0.57
     also
    0.55
     myös
    0.55
     også
    0.55
     recently
    0.54
    formerly
    0.53
     had
    0.52
     ehemalige
    0.52
     former
    0.52
    Activations Density 0.096%

    No Known Activations