© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142294
    Prev
    Next
    INDEX
    Explanations

    volume indicators

    np_acts-logits-general · gemini-2.5-flash-lite

    quirky, complex, trick, framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يه
    0.50
    갤
    0.49
     činjen
    0.48
    נים
    0.47
    资产
    0.47
    ös
    0.47
    ني
    0.46
    执
    0.46
    ية
    0.45
    يش
    0.43
    POSITIVE LOGITS
     ribbed
    0.47
     Vice
    0.46
     Knee
    0.45
     knees
    0.45
     downregulation
    0.45
     leucine
    0.45
     NOVEMBER
    0.45
    insensitive
    0.44
     DECEMBER
    0.43
     夏季
    0.43
    Activations Density 0.001%

    No Known Activations