© 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. 145611
    Prev
    Next
    INDEX
    Explanations

    displaying IP addresses

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

    legal and safe

    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
     analyzers
    0.47
     iā
    0.46
     f
    0.45
    ყ
    0.44
     decouple
    0.44
     ф
    0.43
    殲
    0.42
     супер
    0.41
     ک
    0.41
    ف
    0.41
    POSITIVE LOGITS
    ocur
    0.57
     furthering
    0.51
    Substring
    0.50
    achev
    0.50
     محافظة
    0.48
     Parks
    0.47
    othe
    0.46
    мітки
    0.46
     一般
    0.46
    ﭑ
    0.45
    Activations Density 0.001%

    No Known Activations