© 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. 22-GEMMASCOPE-RES-131K
    7. 26556
    Prev
    Next
    INDEX
    Explanations

    C orator

    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_22/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
     Most
    -0.99
     Scott
    -0.81
     In
    -0.81
     Even
    -0.79
     continued
    -0.77
     Very
    -0.77
     Going
    -0.77
     Still
    -0.77
    ombes
    -0.74
     E
    -0.73
    POSITIVE LOGITS
     архив
    0.96
    战术
    0.89
     cursus
    0.86
    卝
    0.85
     geel
    0.85
     ſur
    0.85
     nus
    0.85
     parlement
    0.85
     borse
    0.84
     bougies
    0.84
    Activations Density 0.115%

    No Known Activations