© 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. 116050
    Prev
    Next
    INDEX
    Explanations

    Express Cruisers

    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
    ➧
    -0.75
     ресни
    -0.73
     mansions
    -0.73
     период
    -0.72
    rilis
    -0.72
    رش
    -0.70
    baiki
    -0.68
     śnie
    -0.68
     sujetos
    -0.68
     叶
    -0.68
    POSITIVE LOGITS
     bunk
    0.91
    KZ
    0.84
    ressão
    0.78
     choreographer
    0.77
     hiper
    0.76
    ylase
    0.75
     washer
    0.75
    érica
    0.75
     Keystone
    0.75
     森
    0.74
    Activations Density 0.006%

    No Known Activations