© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109664
    Prev
    Next
    INDEX
    Explanations

    program

    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
    Shortly
    -0.87
    idać
    -0.77
    Nearly
    -0.76
    𝖒
    -0.76
    さんです
    -0.76
     {
    -0.74
    zków
    -0.74
     компонен
    -0.73
    Gator
    -0.72
    katkan
    -0.71
    POSITIVE LOGITS
    program
    1.08
    ramp
    1.06
    held
    1.06
     programmed
    0.97
     program
    0.94
     ramp
    0.93
     PROGRAM
    0.92
    programming
    0.87
     програм
    0.87
     vitesse
    0.87
    Activations Density 0.020%

    No Known Activations