© 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. 19737
    Prev
    Next
    INDEX
    Explanations

    celestial names

    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
    0
    -3.05
    1
    -2.61
    \
    -2.59
     повітря
    -2.42
    基本上
    -2.34
    2
    -2.28
    }
    -2.25
     jsem
    -2.19
    नलोड
    -2.17
    或者
    -2.14
    POSITIVE LOGITS
     be
    2.86
    瑒
    2.56
    ]
    2.45
    噲
    2.36
    趼
    2.30
    嵛
    2.17
    邶
    2.09
    </i>
    2.09
     atrav
    2.06
     sensação
    2.00
    Activations Density 0.002%

    No Known Activations