© 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. 57633
    Prev
    Next
    INDEX
    Explanations

    production output

    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
    }
    -2.27
    可能有
    -1.74
    ;
    -1.57
    </td>
    -1.57
    隂
    -1.40
     Maternal
    -1.37
     Our
    -1.31
     교육
    -1.30
    也不能
    -1.28
     пользователем
    -1.27
    POSITIVE LOGITS
    lamó
    1.63
    𞤤
    1.41
    Jahre
    1.41
    嵛
    1.35
     sintió
    1.29
    prá
    1.28
     acogedor
    1.27
    deln
    1.27
    这里
    1.25
     знамени
    1.25
    Activations Density 0.038%

    No Known Activations