© 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. 143622
    Prev
    Next
    INDEX
    Explanations

    you cry

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

    universal moral principles

    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
     вико
    0.49
     inconsider
    0.49
     [...]
    0.48
     deaktiv
    0.48
     Abou
    0.47
     Jérôme
    0.47
     Alyssa
    0.46
     vincul
    0.46
     Sylvie
    0.46
    がか
    0.45
    POSITIVE LOGITS
    常用
    0.48
    খে
    0.48
    频率
    0.48
    '
    0.46
    ita
    0.45
    Frequency
    0.44
    ೇವ
    0.44
    ITA
    0.43
    OS
    0.43
    핏
    0.43
    Activations Density 0.000%

    No Known Activations