© 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. 228369
    Prev
    Next
    INDEX
    Explanations

    semantic contexts surrounding words like "side", "Bald Eagle", "chips", and foreign words

    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
     mapDispatch
    0.46
    jobNumber
    0.46
    MiddleLine
    0.45
    дию
    0.45
    斛
    0.45
     लौटे
    0.44
     bitOp
    0.43
     AppCompatTheme
    0.43
     Microscopy
    0.43
    玹
    0.43
    POSITIVE LOGITS
    स्वी
    0.52
    1
    0.48
    ligt
    0.48
    isf
    0.47
    Stanley
    0.47
     miracles
    0.46
     завжди
    0.45
     আজ
    0.44
    fé
    0.44
     rockets
    0.44
    Activations Density 0.001%

    No Known Activations