© 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. 90767
    Prev
    Next
    INDEX
    Explanations

    Candida, Quaker, accountId, CFL, CCP, respuesta

    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
    .';
    -2.72
    ⻬
    -2.67
    
    -2.67
    lossians
    -2.61
    StoryboardSegue
    -2.42
     但
    -2.30
    を用
    -2.28
    很赞
    -2.23
    蚡
    -2.23
     ";
    -2.22
    POSITIVE LOGITS
    i
    2.94
    </b>
    2.78
    ஂ
    2.69
    an
    2.63
    on
    2.47
    ⢂
    2.42
    </h5>
    2.39
    g
    2.39
    我
    2.20
    鏖
    2.20
    Activations Density 0.002%

    No Known Activations