© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32314
    Prev
    Next
    INDEX
    Explanations

    specific items or data

    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
     récente
    -1.05
     éstas
    -1.00
    的女人
    -1.00
     ésta
    -0.93
     frecuentemente
    -0.92
    ⊳
    -0.91
     mecánico
    -0.91
     czeka
    -0.90
    entrums
    -0.89
     orgánico
    -0.88
    POSITIVE LOGITS
     creation
    2.58
     acquisition
    2.17
     implementation
    1.91
     generation
    1.84
     placement
    1.80
     issuance
    1.78
     deployment
    1.74
    creation
    1.74
     removal
    1.74
     preparation
    1.74
    Activations Density 0.432%

    No Known Activations