© 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. 242488
    Prev
    Next
    INDEX
    Explanations

    "WHAT" DISCOUNTS or prices

    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
    episode
    0.46
     marathon
    0.43
     episode
    0.43
     episodes
    0.42
     intertwined
    0.42
     intertw
    0.41
    martial
    0.41
    劍
    0.41
     aquel
    0.41
    deutsch
    0.41
    POSITIVE LOGITS
     Canva
    0.47
    StudentNo
    0.45
     spä
    0.44
     langchain
    0.44
     plantel
    0.43
    ünden
    0.42
     Kaltura
    0.42
    رے
    0.42
    illaume
    0.42
    📍
    0.42
    Activations Density 0.000%

    No Known Activations