© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15079
    Prev
    Next
    INDEX
    Explanations

    Java and programming setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muni
    0.57
     struggled
    0.55
     blasp
    0.55
     struggle
    0.50
     त्रि
    0.49
     का
    0.49
    ͎
    0.49
     explosive
    0.48
     оюндары
    0.48
     dabb
    0.48
    POSITIVE LOGITS
     JavaVersion
    0.72
    ྫ
    0.57
    dong
    0.54
     বাঙ্গালা
    0.54
    culoskeletal
    0.52
     命令
    0.51
    <unused83>
    0.50
     record
    0.50
    جة
    0.50
    Java
    0.50
    Activations Density 0.076%

    No Known Activations