© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3632
    Prev
    Next
    INDEX
    Explanations

    Python library imports for data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    sp
    0.65
    RTT
    0.64
     Week
    0.62
    TOR
    0.62
     WS
    0.62
    EW
    0.62
    ◕
    0.61
    enei
    0.61
     Release
    0.61
    ريك
    0.60
    POSITIVE LOGITS
    マ
    0.70
     তোলেন
    0.64
     madre
    0.63
     nap
    0.63
     دیده
    0.63
     मा
    0.62
    タブ
    0.61
     নিবন্ধ
    0.61
    玛
    0.61
    瑪
    0.60
    Activations Density 0.275%

    No Known Activations