© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3486
    Prev
    Next
    INDEX
    Explanations

    main series

    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_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
    த
    1.33
    cribing
    1.23
    いう
    1.21
    𝖊
    1.20
    ţi
    1.18
     وفي
    1.18
    બ
    1.18
    𝖐
    1.17
    chlor
    1.16
    AT
    1.15
    POSITIVE LOGITS
    テナンス
    1.81
    stays
    1.75
     competencies
    1.39
    nnet
    1.38
    nets
    1.36
     tenets
    1.32
    sächlich
    1.23
    nál
    1.23
    та
    1.22
     pundits
    1.22
    Activations Density 0.501%

    No Known Activations