© 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. 17183
    Prev
    Next
    INDEX
    Explanations

    david followed by names

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

    david followed by names

    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
     ছিলনা
    0.41
    FOLDER
    0.37
    방법
    0.36
    PRODUCTS
    0.36
     treats
    0.36
     طبعا
    0.35
     strikes
    0.35
    穩
    0.35
     Enfin
    0.34
     stops
    0.34
    POSITIVE LOGITS
     Goliath
    0.52
    David
    0.50
     David
    0.49
    榇
    0.40
     david
    0.40
    oliath
    0.39
    êu
    0.38
     dave
    0.38
    ész
    0.38
    DAVID
    0.38
    Activations Density 0.028%

    No Known Activations