Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 7617
    Prev
    Next
    INDEX
    Explanations

    CSS features like variables and frameworks

    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
    ത്വം
    0.38
    遑
    0.37
     kalan
    0.37
    ==
    0.37
     Pm
    0.36
     convent
    0.36
    Cxx
    0.35
    σιν
    0.35
    ncnc
    0.34
    ள்ளன
    0.34
    POSITIVE LOGITS
    CSS
    0.48
     갔
    0.46
     Grid
    0.46
    ɢ
    0.42
    文件
    0.41
     Schall
    0.41
     限
    0.41
     advancements
    0.40
     CSS
    0.40
    Hooks
    0.40
    Activations Density 0.005%

    No Known Activations