© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11047
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

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

    amounts of specific items

    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
     অল্প
    0.53
    几十
    0.48
    長時間
    0.46
    一段时间
    0.45
    多年
    0.43
    amount
    0.43
    长时间
    0.42
    几
    0.42
     longue
    0.41
    位数
    0.41
    POSITIVE LOGITS
     apiece
    0.54
     (!)
    0.52
     ناقابل
    0.51
     nearest
    0.48
     consecutivos
    0.47
     compteur
    0.46
     consecut
    0.45
     respectivamente
    0.45
     promedio
    0.44
    বিশিষ্ট
    0.43
    Activations Density 0.508%

    No Known Activations