© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34619
    Prev
    Next
    INDEX
    Explanations

    tracing origins and development

    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
    Negative Logits
    我相信
    2.20
    𝖊
    2.03
    কিন্ত
    2.00
    lerde
    1.85
    有很多
    1.81
    辕
    1.80
    𝘁
    1.80
    🔥🔥
    1.77
    いろんな
    1.73
    𝗻
    1.70
    POSITIVE LOGITS
    a
    2.34
    e
    2.28
    y
    2.25
    ру
    2.14
    er
    2.02
    ির
    1.98
    רות
    1.98
    ров
    1.96
     рода
    1.84
    ר
    1.84
    Activations Density 0.008%

    No Known Activations