© 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. 90045
    Prev
    Next
    INDEX
    Explanations

    #4 ranking

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

    even if, even in

    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
     wreak
    0.50
    鲨
    0.48
     courbe
    0.46
     drž
    0.45
    auch
    0.44
     मशहूर
    0.44
    sız
    0.44
     isla
    0.44
     professionnels
    0.44
     vrste
    0.43
    POSITIVE LOGITS
    К
    0.49
     کد
    0.45
    gador
    0.45
    gtrsim
    0.44
     getters
    0.44
    দিনের
    0.43
     لی
    0.42
    щего
    0.42
     הג
    0.41
    Га
    0.41
    Activations Density 0.001%

    No Known Activations