© 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. 130890
    Prev
    Next
    INDEX
    Explanations

    fairy tales, realms, queen, dust

    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
    ໊
    -2.47
     leaſt
    -2.44
    ↵
    -2.36
    佉
    -2.36
    附近的
    -2.36
    珝
    -2.31
    亖
    -2.28
    但是在
    -2.22
     für
    -2.22
    ?"
    -2.20
    POSITIVE LOGITS
    }
    2.91
    </i>
    2.88
     BIBLIO
    2.58
    and
    2.48
    鈀
    2.42
    艫
    2.41
    %
    2.38
    ⡱
    2.36
    ܆
    2.31
    </h3>
    2.25
    Activations Density 0.003%

    No Known Activations