© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21833
    Prev
    Next
    INDEX
    Explanations

    Data Link, Network

    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_40_width_262k_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
    thebetter
    0.42
     يحت
    0.38
    duit
    0.38
    imm
    0.38
    ']),
    0.36
    fli
    0.36
    二氧化
    0.36
    ধির
    0.36
     syphilit
    0.36
     ガラス
    0.36
    POSITIVE LOGITS
     creencias
    0.39
     afectan
    0.37
     Gracie
    0.37
    增加
    0.36
    ancia
    0.35
     religiosas
    0.35
     অর্থনীতি
    0.35
    Readers
    0.35
    膳
    0.35
     encerr
    0.34
    Activations Density 0.000%

    No Known Activations