© 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. 199408
    Prev
    Next
    INDEX
    Explanations

    know that or understand your

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

    Protestant work ethic vs privacy

    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
     untuk
    0.52
     atau
    0.52
     coba
    0.51
     mock
    0.50
     ś
    0.49
     terse
    0.49
     explica
    0.49
     época
    0.49
     berdasarkan
    0.49
     correlates
    0.49
    POSITIVE LOGITS
    天使
    0.49
    ᔾ
    0.48
    臀
    0.48
    れて
    0.46
    良
    0.46
    Starburst
    0.46
    運動
    0.45
    很多人
    0.45
    هرة
    0.44
    鬱
    0.44
    Activations Density 0.001%

    No Known Activations