© 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. 655
    Prev
    Next
    INDEX
    Explanations

    research papers and figures

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

    academic abstracts and theses

    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
    ⚋
    0.53
    ത്തിറ
    0.52
    ihanna
    0.52
    銀行
    0.49
    เงิน
    0.48
     télévision
    0.48
     ক্লাব
    0.48
    动漫
    0.47
     calendriers
    0.47
    㮔
    0.47
    POSITIVE LOGITS
     thesis
    0.78
     analysis
    0.78
     Results
    0.77
    論文
    0.77
    文献
    0.75
    Results
    0.75
     research
    0.73
    论文
    0.73
     Research
    0.70
     Thesis
    0.70
    Activations Density 0.169%

    No Known Activations