© 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-65K
    7. 405
    Prev
    Next
    INDEX
    Explanations

    list and data processing

    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_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
    kosten
    0.46
    ົດ
    0.43
    k
    0.42
     legitt
    0.42
    d
    0.41
    mathcal
    0.41
     ตำ
    0.41
     treści
    0.41
    ;
    0.41
    internet
    0.40
    POSITIVE LOGITS
     impairs
    0.45
    濋
    0.44
     removes
    0.43
    鹈
    0.43
    وم
    0.43
    衿
    0.42
     الأولى
    0.42
     गेंदबाजी
    0.42
     நிறுத்த
    0.42
    ップ
    0.41
    Activations Density 0.000%

    No Known Activations