© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 260479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FileInfo
    0.44
     Barros
    0.43
    大
    0.42
    BMP
    0.42
     AREAS
    0.42
    YYYY
    0.42
     biste
    0.42
    Mega
    0.42
     funk
    0.41
     Beim
    0.41
    POSITIVE LOGITS
     задач
    0.58
     элект
    0.52
     фа
    0.50
    𝘦
    0.49
     пье
    0.48
     لہ
    0.47
     долларов
    0.46
    addena
    0.46
    溌
    0.46
     цик
    0.46
    Activations Density 0.000%

    No Known Activations