© 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. 132997
    Prev
    Next
    INDEX
    Explanations

    scatter plot figure

    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
    ignées
    0.44
    リューション
    0.44
     تغيير
    0.39
    ÈME
    0.39
    换
    0.38
     response
    0.38
     responds
    0.38
    响应
    0.38
     बदलते
    0.38
    における
    0.38
    POSITIVE LOGITS
    style
    0.40
    skin
    0.40
    鼓
    0.38
    property
    0.38
     skin
    0.38
    ส
    0.38
    ारी
    0.37
     Skin
    0.36
     Style
    0.36
    Style
    0.36
    Activations Density 0.001%

    No Known Activations