© 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. 6331
    Prev
    Next
    INDEX
    Explanations

    Google Doc, falling rock, optimal flight

    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
    nut
    0.48
    राहुल
    0.46
    🌵
    0.46
    aking
    0.46
    Yon
    0.45
    ヨ
    0.45
    ut
    0.45
    aft
    0.44
    Enabled
    0.44
    ib
    0.43
    POSITIVE LOGITS
     cela
    0.42
     cyclists
    0.42
     climate
    0.41
     sureties
    0.41
     рекорд
    0.41
    諡
    0.41
     nucleic
    0.40
     restructured
    0.40
     scl
    0.40
     нового
    0.39
    Activations Density 0.014%

    No Known Activations