© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10258
    Prev
    Next
    INDEX
    Explanations

    specs, download, status, PDF, history, stock, song

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

    breakdown of what

    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_40_width_16k_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
    𝐁
    0.43
    腧
    0.43
     Miscellaneous
    0.40
    炜
    0.40
     刘
    0.40
     यादगार
    0.40
    刘
    0.39
     المللی
    0.39
     Cited
    0.39
     Наши
    0.39
    POSITIVE LOGITS
     details
    0.49
     पूरी
    0.48
     explained
    0.48
     ಇಲ್ಲ
    0.48
    meaning
    0.46
     meaning
    0.45
    }+{\
    0.45
     shocked
    0.44
    full
    0.43
     history
    0.43
    Activations Density 0.180%

    No Known Activations