© 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. 31-GEMMASCOPE-2-RES-262K
    7. 114690
    Prev
    Next
    INDEX
    Explanations

    prayer, called, Bengal, by

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

    `Key? key` constructor parameter

    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_31_width_262k_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
    ढ
    0.45
    いますが
    0.44
    電池
    0.41
     moyennes
    0.40
    enação
    0.39
    きましたが
    0.39
    الا
    0.39
     contraindicated
    0.38
    database
    0.38
     mesmas
    0.38
    POSITIVE LOGITS
     başladı
    0.52
     माध्यमातून
    0.49
    我们可以
    0.48
     formContext
    0.47
    畯
    0.47
     समुदाय
    0.46
    ത്തന
    0.46
    剑
    0.46
    贤
    0.46
    ים
    0.45
    Activations Density 0.000%

    No Known Activations