© 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. 218356
    Prev
    Next
    INDEX
    Explanations

    occupy Paris or reserves

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

    words followed by descriptors

    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
    榕
    0.52
     직선
    0.50
    🗯
    0.48
     তিনিও
    0.47
     शॉर्ट
    0.46
     短
    0.46
     בה
    0.46
     *-
    0.46
     അന്വേഷ
    0.46
    endaft
    0.45
    POSITIVE LOGITS
     ritrov
    0.43
    গুলির
    0.42
    setVerticalGroup
    0.40
     monotonically
    0.39
     tuck
    0.39
    ز
    0.38
    HC
    0.38
     doz
    0.38
     commerciales
    0.37
     malignancies
    0.37
    Activations Density 0.000%

    No Known Activations