© 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. 12-GEMMASCOPE-2-RES-262K
    7. 37692
    Prev
    Next
    INDEX
    Explanations

    infectious, replication, polygraph, forging

    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_12_width_262k_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
    en
    1.64
    ті
    1.55
    liness
    1.47
    okkh
    1.42
    埤
    1.41
    وانی
    1.34
    풋
    1.34
    戙
    1.34
     związ
    1.34
    ักษณะ
    1.33
    POSITIVE LOGITS
    1.25
     לא
    1.22
    وت
    1.17
     to
    1.11
     तो
    1.08
     doesn
    1.06
    ور
    1.05
    ไม่
    1.05
    দিনের
    1.03
     ਨੇ
    1.02
    Activations Density 0.000%

    No Known Activations