© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2855
    Prev
    Next
    INDEX
    Explanations

    Stillness or Still Alive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
     builder
    0.40
     zů
    0.38
     sheared
    0.35
    둥
    0.35
     slashed
    0.35
     vésicules
    0.35
     consistently
    0.34
     scratches
    0.34
    Sys
    0.34
     الإص
    0.34
    POSITIVE LOGITS
    angnya
    0.50
     Gage
    0.39
    ຫນ
    0.38
    ড্ড
    0.38
     Still
    0.37
    可能性
    0.37
    aman
    0.37
    ᴺ
    0.36
    did
    0.36
    engono
    0.35
    Activations Density 0.005%

    No Known Activations