© 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. 268
    Prev
    Next
    INDEX
    Explanations

    graph TD

    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
    牝
    0.41
    輸出
    0.40
     परिवर्तन
    0.40
    uradaki
    0.39
    olition
    0.39
     outil
    0.38
     naturelles
    0.38
    творення
    0.38
     espaços
    0.38
    输出
    0.37
    POSITIVE LOGITS
    尚
    0.39
    class
    0.39
    package
    0.38
    mid
    0.38
     Package
    0.37
     package
    0.36
     bede
    0.36
     FB
    0.35
     Mid
    0.35
     Duk
    0.35
    Activations Density 0.004%

    No Known Activations