© 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. 10913
    Prev
    Next
    INDEX
    Explanations

    emoticons and closings

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

    polite closing with emoji

    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
    为
    0.40
    Choose
    0.38
    Disease
    0.37
    Natural
    0.37
     Disease
    0.35
    是
    0.35
    是可以
    0.35
     Sacrifice
    0.35
    ittle
    0.34
    imetry
    0.34
    POSITIVE LOGITS
    ྩ
    0.46
    निष्
    0.40
     jov
    0.39
     upregulated
    0.38
     ー
    0.38
     dünyaya
    0.38
     aprob
    0.37
    ков
    0.37
     activations
    0.37
    𝖺
    0.37
    Activations Density 0.010%

    No Known Activations