© 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. 2386
    Prev
    Next
    INDEX
    Explanations

    code or technical text identifiers

    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
     CRUZ
    -0.81
     tensors
    -0.80
    Cruz
    -0.80
    zani
    -0.78
     炒
    -0.75
     Гон
    -0.75
    ⊞
    -0.72
     válvulas
    -0.72
     memulai
    -0.71
     issu
    -0.70
    POSITIVE LOGITS
    dataType
    0.95
     host
    0.70
     dataType
    0.69
    ’.
    0.67
     consuma
    0.66
    捧
    0.66
    òm
    0.65
    청
    0.65
    Plots
    0.65
    inho
    0.65
    Activations Density 0.028%

    No Known Activations