© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3043
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ২০১৮
    0.95
     ২০১৭
    0.88
     ২০১৬
    0.86
    ⚉
    0.85
    Coronavirus
    0.84
     ۲۰۱
    0.84
     नोटबंदी
    0.80
     ২০১৫
    0.76
     AdWords
    0.76
    Brexit
    0.75
    POSITIVE LOGITS
    🫠
    1.20
    🫶
    1.14
    🥹
    1.09
    🫣
    1.08
     ChatGPT
    1.06
    🫢
    1.05
    🫡
    1.00
    🫰
    0.96
    ChatGPT
    0.96
    🩶
    0.93
    Activations Density 0.878%

    No Known Activations