© 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. 14723
    Prev
    Next
    INDEX
    Explanations

    stats, ids, or variable values

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

    configuration parameters and settings

    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
    Estas
    0.42
    ೆಯನ್ನು
    0.40
    Е
    0.39
     ხ
    0.39
    Estado
    0.39
    ITIVE
    0.38
    nese
    0.37
    Estos
    0.37
     나무
    0.37
    ტერ
    0.37
    POSITIVE LOGITS
     với
    0.46
     με
    0.45
     avec
    0.42
     with
    0.42
     {
    0.40
     affiliated
    0.40
     сё
    0.39
    يت
    0.38
     kwargs
    0.38
     Monument
    0.38
    Activations Density 0.000%

    No Known Activations