© 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. 16757
    Prev
    Next
    INDEX
    Explanations

    action descriptions

    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
     mohli
    0.42
    觛
    0.41
     സമൂഹ
    0.41
     могли
    0.40
     ሃ
    0.40
     માત્ર
    0.40
     হয়েছিল
    0.39
     বলেছিলেন
    0.39
     ಒಂದ
    0.39
     భాష
    0.39
    POSITIVE LOGITS
     enthusi
    0.47
    pping
    0.44
     Jing
    0.44
     realises
    0.44
    同时也
    0.41
    reibt
    0.41
     mistakenly
    0.40
    oooooooo
    0.40
     J
    0.40
     কর্তৃক
    0.40
    Activations Density 0.056%

    No Known Activations