© 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. 70699
    Prev
    Next
    INDEX
    Explanations

    MJ or J followed by names/initials

    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
    ;
    -3.34
    );
    -2.94
    l
    -2.61
    ”.
    -2.56
    ”
    -2.53
     accented
    -2.39
    </sub>
    -2.39
    );
    -2.38
    ,"
    -2.36
    ).
    -2.25
    POSITIVE LOGITS
    赑
    2.48
    鮸
    2.44
     ſch
    2.33
    鴴
    2.25
    鹮
    2.23
     legati
    2.22
    ᷆
    2.19
    珰
    2.17
    쨩
    2.09
    ѣмъ
    2.05
    Activations Density 0.003%

    No Known Activations