© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163783
    Prev
    Next
    INDEX
    Explanations

    tracking device

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

    considerations, warnings, or advice

    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
     Approximation
    0.46
     Adjacent
    0.45
     জীবের
    0.44
    巧
    0.44
     Offshore
    0.43
     Fundamentals
    0.43
     curtains
    0.43
     Architecture
    0.43
    大量的
    0.42
    േ
    0.41
    POSITIVE LOGITS
    फल
    0.51
    usaha
    0.47
     troubled
    0.46
     taşı
    0.45
    निया
    0.45
     которых
    0.45
    ડિયો
    0.45
     reward
    0.45
    Przyp
    0.45
    Records
    0.44
    Activations Density 0.001%

    No Known Activations