© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9479
    Prev
    Next
    INDEX
    Explanations

    when something goes wrong

    np_acts-logits-general · gemini-2.5-flash-lite

    describing quantities or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused100>
    0.41
     |,
    0.40
    _,
    0.39
    <unused2110>
    0.39
     우리는
    0.39
     ਤੁਸੀਂ
    0.39
     는
    0.38
    \},
    0.36
     reikia
    0.36
    <unused2197>
    0.36
    POSITIVE LOGITS
    不已
    0.46
    之一
    0.41
     குறித்து
    0.41
    ynchus
    0.40
    且
    0.40
    abouts
    0.39
    และการ
    0.38
    相结合
    0.38
    اء
    0.38
    ிருப்பது
    0.38
    Activations Density 0.209%

    No Known Activations