© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65068
    Prev
    Next
    INDEX
    Explanations

    always, all, immediately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    所以我
    -2.73
    “
    -2.47
    但我
    -2.47
    $
    -2.27
    因而
    -2.19
    </sup>
    -2.17
    mentação
    -2.17
    apartamento
    -2.14
     hinder
    -2.13
    desliz
    -2.08
    POSITIVE LOGITS
    you
    2.61
    replyreport
    2.16
     "..\..\..\
    2.16
    錒
    2.14
    that
    2.14
     dopo
    2.06
    %;
    2.03
    媖
    2.03
    }();
    2.00
    ))=\
    1.99
    Activations Density 0.001%

    No Known Activations