© 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. 245936
    Prev
    Next
    INDEX
    Explanations

    when or if describing conditions

    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
    ↵
    0.51
     LI
    0.50
     QUANT
    0.49
     Loading
    0.46
     web
    0.45
     dropdown
    0.45
     ADAM
    0.45
     subset
    0.45
     D
    0.44
     matplotlib
    0.44
    POSITIVE LOGITS
     وقتی
    0.58
     अगले
    0.56
     அடிக்க
    0.56
     दौड़
    0.55
     این
    0.55
     જાહેર
    0.54
     അല്ലെങ്കിൽ
    0.54
    ഒരു
    0.54
     якщо
    0.53
     що
    0.53
    Activations Density 0.000%

    No Known Activations