© 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. 100746
    Prev
    Next
    INDEX
    Explanations

    of things and place

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

    asset types

    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
    ife
    0.42
     بدون
    0.41
    پ
    0.41
    ências
    0.40
      
    0.40
     عند
    0.39
    agus
    0.39
    وک
    0.39
     in
    0.39
     e
    0.38
    POSITIVE LOGITS
     creada
    0.51
    떻
    0.50
     나라
    0.50
     使っ
    0.50
     הייתה
    0.49
    娀
    0.49
    쟤
    0.49
     考え
    0.48
     言っ
    0.48
     យើង
    0.48
    Activations Density 0.000%

    No Known Activations