© 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. 17955
    Prev
    Next
    INDEX
    Explanations

    Pickup from storage

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

    how can I

    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
    datei
    0.45
     dispone
    0.43
    পাশের
    0.42
    栲
    0.41
    ಕಾರಿ
    0.41
    வையும்
    0.41
    <unused25>
    0.40
    য়েছে
    0.40
    водить
    0.40
     ایکسپ
    0.40
    POSITIVE LOGITS
     ""){
    0.39
     unser
    0.38
     sprinkle
    0.38
     folks
    0.37
     Tw
    0.37
    tw
    0.37
    هر
    0.36
     further
    0.36
     tw
    0.36
     adorn
    0.36
    Activations Density 0.000%

    No Known Activations