© 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. 92771
    Prev
    Next
    INDEX
    Explanations

    Regional followed by diverse contexts

    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
     razões
    -1.05
    
    -0.98
     fonctionnent
    -0.97
     Mindfulness
    -0.91
     méthodes
    -0.91
     regiões
    -0.90
    
    -0.90
     มี
    -0.90
     quelcon
    -0.90
     области
    -0.88
    POSITIVE LOGITS
    ism
    1.46
    ization
    1.28
    ized
    1.24
    ist
    1.14
     variations
    1.00
    isation
    0.99
     offices
    0.97
    b
    0.97
    _
    0.96
    istic
    0.94
    Activations Density 0.015%

    No Known Activations