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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5317
    Prev
    Next
    INDEX
    Explanations

    versions of models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    {
    0.59
    ح
    0.54
    ش
    0.51
    一丝
    0.49
    _
    0.48
     Deli
    0.47
     Garbage
    0.46
     {
    0.46
    نا
    0.45
    يسي
    0.45
    POSITIVE LOGITS
    ＂
    0.56
     ५
    0.54
    ourent
    0.52
    ↵↵
    0.52
    ции
    0.50
    ্ক
    0.50
    \";
    0.50
    uencia
    0.49
    ﻂ
    0.49
    ”;
    0.48
    Activations Density 0.002%

    No Known Activations