© 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. 13627
    Prev
    Next
    INDEX
    Explanations

    reporting positive feedback

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

    expressing thanks and congratulations

    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
     Nhưng
    0.48
     আদাল
    0.47
     მაგრამ
    0.47
     μαύ
    0.46
     但是
    0.46
     दगडा
    0.46
     ক্ষেত্রেই
    0.46
    ཋ
    0.45
    還是
    0.44
    無視
    0.44
    POSITIVE LOGITS
     congratulated
    0.81
     thanked
    0.69
     congrat
    0.68
     felicit
    0.67
     congratulate
    0.65
     commended
    0.65
     welcomed
    0.65
     praised
    0.63
     congratulations
    0.63
     congrats
    0.62
    Activations Density 0.036%

    No Known Activations