© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15290
    Prev
    Next
    INDEX
    Explanations

    results and "show"

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

    performance evaluation

    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_16k_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
     modulates
    0.68
     molecular
    0.64
     redox
    0.63
     perox
    0.61
     parallel
    0.61
     correlated
    0.61
     insoluble
    0.60
     yellow
    0.59
     modified
    0.59
     soluble
    0.59
    POSITIVE LOGITS
    营收
    0.75
     результа
    0.67
     стаўкі
    0.67
     测试
    0.66
    的价格
    0.66
    收费
    0.66
    览
    0.65
    用户名
    0.64
    璈
    0.64
    的市场
    0.63
    Activations Density 0.064%

    No Known Activations