© 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. 14700
    Prev
    Next
    INDEX
    Explanations

    code generation or interface elements

    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
     Sensitive
    0.57
     auftreten
    0.57
     passwords
    0.57
     Password
    0.56
     quím
    0.55
     நடைபெ
    0.54
     Raw
    0.54
     `.
    0.53
     Plants
    0.53
     그림
    0.53
    POSITIVE LOGITS
    acal
    0.61
    लेंट
    0.58
    avian
    0.56
    ंनो
    0.53
     сезон
    0.53
     ejercer
    0.53
    ývá
    0.53
    חיל
    0.52
    ActionResult
    0.52
     ஒலி
    0.52
    Activations Density 0.000%

    No Known Activations