© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5473
    Prev
    Next
    INDEX
    Explanations

    doing / to do

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

    to do

    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_53_width_65k_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
     ګرځ
    0.38
     وګ
    0.37
    睇
    0.35
    ongan
    0.33
    使える
    0.32
    lookandfeel
    0.32
    цам
    0.32
    ед
    0.31
    ടങ്ങ
    0.31
     ਕਿ
    0.30
    POSITIVE LOGITS
     doing
    3.78
     Doing
    3.73
    Doing
    3.72
    doing
    3.58
    做
    2.86
     hacerlo
    2.84
     melakukannya
    2.69
     lakukan
    2.66
    ทำ
    2.61
     doen
    2.61
    Activations Density 1.040%

    No Known Activations