© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13884
    Prev
    Next
    INDEX
    Explanations

    measurement and testing

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

    methods for detection or analysis

    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
     మహా
    0.46
     manoeuv
    0.46
    יוחד
    0.42
    耶路撒
    0.41
    ེ
    0.41
     maneu
    0.41
     protagon
    0.41
     மலை
    0.41
     $("<
    0.41
    AllFilesIn
    0.41
    POSITIVE LOGITS
     detecting
    0.93
    检测
    0.90
     detección
    0.85
     Detecting
    0.85
     monitoring
    0.84
     biomarkers
    0.82
     Detect
    0.81
     detection
    0.80
     Predictive
    0.80
    detection
    0.79
    Activations Density 0.717%

    No Known Activations