© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7156
    Prev
    Next
    INDEX
    Explanations

    programming language imports and declarations

    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
     Manitoba
    -0.81
    autorelease
    -0.77
     Chandigarh
    -0.74
    čilo
    -0.74
    iería
    -0.72
     Konto
    -0.72
    タイヤ
    -0.71
     Trot
    -0.71
     bodas
    -0.71
     erik
    -0.70
    POSITIVE LOGITS
     Zeiss
    0.94
    EObject
    0.88
    xtext
    0.88
    rrer
    0.87
    serializer
    0.84
     Ambient
    0.82
     DSL
    0.81
    pektrum
    0.79
     dissolving
    0.77
     cev
    0.77
    Activations Density 0.013%

    No Known Activations