© 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. 78972
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

    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
    anggap
    -0.82
    ressible
    -0.77
     Glaub
    -0.76
     multifunctional
    -0.75
     onCancelled
    -0.75
     života
    -0.74
     robus
    -0.74
    报记者
    -0.73
     createState
    -0.73
    layout
    -0.73
    POSITIVE LOGITS
     manual
    0.92
     نے
    0.91
     писто
    0.91
    none
    0.90
     normal
    0.90
     σελ
    0.89
     none
    0.87
     sì
    0.85
    mmHg
    0.84
    yes
    0.82
    Activations Density 0.094%

    No Known Activations