© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74793
    Prev
    Next
    INDEX
    Explanations

    preparation, planning, application

    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
     может
    -1.73
    //
    -1.63
     $
    -1.60
    ="
    -1.60
     /
    -1.59
    ."
    -1.47
     могут
    -1.43
    5
    -1.37
    <b>
    -1.36
    UnityEngine
    -1.34
    POSITIVE LOGITS
     castelo
    1.89
     手绘
    1.74
     花卉
    1.72
     edifício
    1.63
     Japão
    1.61
    呖
    1.55
     trouva
    1.55
     ſont
    1.52
     Portugu
    1.52
     monumento
    1.51
    Activations Density 0.008%

    No Known Activations