© 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. 197948
    Prev
    Next
    INDEX
    Explanations

    economically competitive

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

    Chinese spoon

    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
     பல
    0.51
    циони
    0.50
    幀
    0.50
     BRIEF
    0.48
     PROBLEMS
    0.46
     MODERN
    0.46
    aronder
    0.46
    龕
    0.46
    ̣i
    0.45
     বিকা
    0.44
    POSITIVE LOGITS
     icy
    0.46
     Fahrt
    0.45
    Paris
    0.43
    Bm
    0.42
    拢
    0.42
     adhesives
    0.42
    Api
    0.41
     rowing
    0.40
     upright
    0.40
     Mainz
    0.39
    Activations Density 0.001%

    No Known Activations