© 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. 40322
    Prev
    Next
    INDEX
    Explanations

    private service

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

    InitializeComponent(); or tens place

    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
     universities
    0.51
    _
    0.49
     actes
    0.48
     faculties
    0.48
     regression
    0.46
     numbers
    0.46
     kav
    0.46
     literary
    0.46
    ecture
    0.45
    退
    0.45
    POSITIVE LOGITS
     წყ
    0.52
     מי
    0.51
     బల
    0.48
     وان
    0.48
    Otra
    0.47
     פרו
    0.46
     Испа
    0.46
     المجال
    0.46
     вызыва
    0.45
    ريبا
    0.45
    Activations Density 0.001%

    No Known Activations