© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44052
    Prev
    Next
    INDEX
    Explanations

    Есть ссылка

    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
    </sup>
    -3.27
    ,"
    -3.23
    -3.03
    </strong>
    -3.00
    ]
    -2.84
    ،
    -2.75
    欷
    -2.73
    </h4>
    -2.72
    </em>
    -2.69
    genodigd
    -2.61
    POSITIVE LOGITS
    虓
    2.91
    \
    2.55
    壜
    2.47
    抬手
    2.44
    低声
    2.33
    开口道
    2.33
     撮っ
    2.27
    工作的
    2.20
    </i>
    2.19
     penchant
    2.17
    Activations Density 0.000%

    No Known Activations