© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    would be

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

    phones, sport, **elite**

    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
     अर
    0.43
     sb
    0.42
     অঞ্জ
    0.42
     ಮತ್ತ
    0.41
    సూరు
    0.41
    锑
    0.41
     Сти
    0.41
    ʰ
    0.39
    campfire
    0.39
     prong
    0.39
    POSITIVE LOGITS
     choke
    0.43
     endeavour
    0.42
     naturally
    0.42
     blot
    0.40
     endeavor
    0.40
     mix
    0.39
     recomb
    0.39
     elapse
    0.39
     result
    0.38
     slow
    0.37
    Activations Density 0.000%

    No Known Activations