© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8592
    Prev
    Next
    INDEX
    Explanations

    software and platforms

    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_16k_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
    cik
    0.44
    ло
    0.42
    jà
    0.41
    िद
    0.40
    tà
    0.40
    蜚
    0.39
    厂
    0.38
    ás
    0.38
    issimo
    0.38
    requestCode
    0.38
    POSITIVE LOGITS
     software
    0.71
     softwares
    0.67
     platforms
    0.63
    software
    0.52
     plataformas
    0.51
    platforms
    0.50
     logiciel
    0.49
    軟件
    0.48
     logiciels
    0.48
     commercially
    0.47
    Activations Density 0.481%

    No Known Activations