© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190032
    Prev
    Next
    INDEX
    Explanations

    money, taxes, vehicles

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

    federal rules

    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
    裴
    0.49
     paysage
    0.45
     Landschaft
    0.45
    UnderWater
    0.44
     دوم
    0.44
    ء
    0.44
     فون
    0.44
     تطوير
    0.44
     repression
    0.43
    IndexArray
    0.43
    POSITIVE LOGITS
     sapien
    0.47
    んですよね
    0.45
     birthdays
    0.43
    生の
    0.43
     👀
    0.42
    ों
    0.42
     kiosks
    0.42
     chương
    0.41
    _{
    0.40
     😉
    0.40
    Activations Density 0.001%

    No Known Activations