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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 376
    Prev
    Next
    INDEX
    Explanations

    do you questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    的主要
    0.89
    しますが
    0.89
     ($\
    0.88
    が必要です
    0.88
     (£
    0.85
    ませんが
    0.84
    的大
    0.84
    的操作
    0.83
    的管理
    0.81
    ですが
    0.81
    POSITIVE LOGITS
     they
    2.79
     you
    2.68
    they
    2.64
     THEY
    2.40
     họ
    2.40
     они
    2.37
    ?");
    2.36
     YOU
    2.30
     vocês
    2.29
    你們
    2.27
    Activations Density 1.195%

    No Known Activations