© 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. 5735
    Prev
    Next
    INDEX
    Explanations

    why

    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
    ת
    2.98
    ت
    2.55
    ة
    2.39
    ك
    2.28
    ري
    2.20
    دي
    2.06
    𝐭
    2.00
    دو
    1.98
     especificar
    1.98
     poiché
    1.98
    POSITIVE LOGITS
    ்ய
    1.83
    ﺭ
    1.81
    ﻭ
    1.73
    岖
    1.72
    ện
    1.70
     Shades
    1.60
    就是
    1.59
    一共
    1.59
    곡
    1.55
    不太
    1.55
    Activations Density 0.098%

    No Known Activations