© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8761
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    scientific units and measurements

    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_53_width_65k_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
    摈
    0.64
    खुद
    0.61
    जरीवाल
    0.57
    मेस्टर
    0.56
    雱
    0.56
     बांट
    0.55
    荸
    0.55
    जेदार
    0.54
    到时候
    0.54
    न्नई
    0.53
    POSITIVE LOGITS
     ∼
    0.90
    ±
    0.87
    ∼
    0.87
     ±
    0.86
     MPa
    0.81
     nM
    0.81
     kHz
    0.80
    ~
    0.77
     keV
    0.75
    −
    0.75
    Activations Density 0.069%

    No Known Activations