© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21327
    Prev
    Next
    INDEX
    Explanations

    Markdown editor

    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_40_width_262k_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
    勝
    0.41
    裡
    0.40
    eleration
    0.40
    äller
    0.40
    綀
    0.39
    કિસ્
    0.39
    相關
    0.38
    вір
    0.38
    訸
    0.38
     reasoning
    0.37
    POSITIVE LOGITS
     TT
    0.46
     TTS
    0.42
     TSS
    0.41
     mT
    0.41
     TH
    0.41
     TN
    0.41
     TCS
    0.41
     TCA
    0.39
     TTC
    0.38
     TM
    0.38
    Activations Density 0.185%

    No Known Activations