© 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. 86285
    Prev
    Next
    INDEX
    Explanations

    money and bonus funds

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

    emotional cues, feelings, beliefs

    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
    结局
    0.49
    헴
    0.49
     sólida
    0.48
    할
    0.47
    CONCLUSION
    0.46
    羟
    0.46
     раствора
    0.45
    ණ්
    0.45
     OBSERV
    0.45
    량
    0.45
    POSITIVE LOGITS
     Money
    0.55
    money
    0.50
     money
    0.48
    space
    0.46
     space
    0.46
     einen
    0.46
     kuris
    0.45
    moment
    0.45
     which
    0.45
     welcher
    0.45
    Activations Density 0.001%

    No Known Activations