© 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. 10479
    Prev
    Next
    INDEX
    Explanations

    ex or pro prefixes

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

    ex-, pro-, out-, in- prefixes

    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
    杫
    0.56
    心脏
    0.49
    зяй
    0.48
    وڈ
    0.47
     rétrécies
    0.47
    Zhang
    0.47
    㞓
    0.47
     subTest
    0.46
    宻
    0.46
    র
    0.46
    POSITIVE LOGITS
    mi
    0.55
    0.54
    anas
    0.52
    ad
    0.49
    ks
    0.49
    pro
    0.49
    ex
    0.48
    ies
    0.48
    ness
    0.48
     pro
    0.48
    Activations Density 0.040%

    No Known Activations