© 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. 70280
    Prev
    Next
    INDEX
    Explanations

    NDT, ultrasonic guided, corrosion, Recyclable, Computer assisted

    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
    ぼう
    -0.79
     savor
    -0.78
    勁
    -0.76
     modding
    -0.75
     szabad
    -0.75
     westward
    -0.74
    uVar
    -0.73
    ᑭ
    -0.73
     Estas
    -0.73
     варто
    -0.72
    POSITIVE LOGITS
     flaw
    1.16
    paint
    0.98
     indications
    0.98
     ultrason
    0.93
     дефек
    0.92
     defect
    0.90
     flaws
    0.88
     Olympus
    0.88
     discontinuity
    0.85
    NDE
    0.81
    Activations Density 0.038%

    No Known Activations