© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    in addition also besides

    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
     ومع
    0.40
    ).”
    0.40
     &/
    0.39
    )."
    0.38
     +/-
    0.38
     عض
    0.38
     พูด
    0.38
    ではなく
    0.38
    )”.
    0.37
    ❤️❤️
    0.37
    POSITIVE LOGITS
     גם
    0.54
     lainnya
    0.48
     également
    0.46
     another
    0.46
     natomiast
    0.45
     aussi
    0.44
     ايضا
    0.43
     myös
    0.43
     hingegen
    0.43
     również
    0.42
    Activations Density 0.154%

    No Known Activations