© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86496
    Prev
    Next
    INDEX
    Explanations

    Koko Tsurumi

    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
     排行
    -1.25
    ’
    -1.24
    jedno
    -1.24
     utilizados
    -1.23
    𝗝
    -1.22
     Поэтому
    -1.18
    \\
    -1.16
     wich
    -1.13
    тные
    -1.13
     厂家
    -1.13
    POSITIVE LOGITS
    YNAMICS
    1.44
    </b>
    1.39
    usstsein
    1.32
    </code>
    1.31
    icolon
    1.30
    これで
    1.30
    '),
    
    1.30
    колай
    1.30
    ༑
    1.29
    });
    
    
    1.27
    Activations Density 0.008%

    No Known Activations