© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48927
    Prev
    Next
    INDEX
    Explanations

    lua code blocks

    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_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
     lua
    0.46
     Lua
    0.43
    try
    0.43
     nei
    0.41
     tais
    0.40
     dije
    0.40
    inyl
    0.40
    ೌ
    0.40
     модуля
    0.39
     બનાવ
    0.39
    POSITIVE LOGITS
     --
    0.49
    --
    0.47
    ---
    0.42
    IF
    0.41
     PERFORM
    0.39
    local
    0.39
    --',
    0.38
     local
    0.38
    ALY
    0.37
     `--
    0.37
    Activations Density 0.036%

    No Known Activations