© 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. 115783
    Prev
    Next
    INDEX
    Explanations

    code model

    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
    Multivariate
    -0.79
     opnieuw
    -0.75
     nuevamente
    -0.75
     novamente
    -0.74
     đừng
    -0.74
    dune
    -0.74
    aucun
    -0.74
     reichlich
    -0.73
     урна
    -0.72
     Their
    -0.72
    POSITIVE LOGITS
    model
    1.00
    respond
    0.99
    モデル
    0.93
     beans
    0.93
    entity
    0.90
    Model
    0.87
     labios
    0.86
    ñora
    0.84
     modele
    0.83
    request
    0.82
    Activations Density 0.005%

    No Known Activations