© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107211
    Prev
    Next
    INDEX
    Explanations

    layout keywords

    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_34/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
    んや
    -1.03
     dramat
    -1.02
     怎么
    -1.02
     หลัง
    -0.99
     Domaine
    -0.98
    Struktur
    -0.98
     trattano
    -0.96
    饜
    -0.96
     จาก
    -0.95
    合った
    -0.95
    POSITIVE LOGITS
    layout
    1.61
     Layout
    1.55
     Lay
    1.55
     groundwork
    1.41
    Lay
    1.37
     layout
    1.37
     lay
    1.32
     layouts
    1.24
    lay
    1.22
    Layout
    1.12
    Activations Density 0.014%

    No Known Activations