© 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. 37901
    Prev
    Next
    INDEX
    Explanations

    placeholder

    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
    iis
    1.49
    ara
    1.42
    ദീ
    1.41
    i
    1.38
    iende
    1.28
    alya
    1.26
    yah
    1.25
     Truy
    1.25
     Vào
    1.24
     وزی
    1.23
    POSITIVE LOGITS
    箇所
    1.30
     deprecated
    1.30
    сть
    1.27
    ف
    1.26
    го
    1.25
    蟆
    1.16
    appelle
    1.13
    ܀
    1.11
    त्मा
    1.10
     pud
    1.09
    Activations Density 0.002%

    No Known Activations