© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107646
    Prev
    Next
    INDEX
    Explanations

    properties and conditions

    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
     تف
    -0.87
    praš
    -0.84
     beggar
    -0.81
     שיש
    -0.77
    识别
    -0.74
     unexplained
    -0.74
    changeable
    -0.72
    侮
    -0.69
    éticos
    -0.69
    amura
    -0.67
    POSITIVE LOGITS
     properties
    2.52
     property
    2.50
     invariant
    1.95
     Properties
    1.95
    property
    1.88
     invariants
    1.85
     Property
    1.84
    properties
    1.84
    Property
    1.77
    Properties
    1.76
    Activations Density 0.086%

    No Known Activations