© 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. 131411
    Prev
    Next
    INDEX
    Explanations

    property tax

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

    money, arranging, non-negative

    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
    不過
    0.43
     polluted
    0.42
    piper
    0.41
    fabricated
    0.41
     هي
    0.40
    vanie
    0.40
    pollution
    0.40
     '<
    0.39
    hanging
    0.39
    contaminated
    0.39
    POSITIVE LOGITS
     أيضًا
    0.48
    讣
    0.45
     además
    0.43
     mêmes
    0.43
     mencion
    0.43
     أيضا
    0.43
    Bradley
    0.43
    CT
    0.42
     faciles
    0.42
     पीड़िता
    0.41
    Activations Density 0.001%

    No Known Activations