© 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. 7106
    Prev
    Next
    INDEX
    Explanations

    than

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

    kinds of creative content

    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
    ্লো
    0.40
    呿
    0.39
     وسط
    0.38
    الہ
    0.38
    ਣੀ
    0.37
     کرتا
    0.36
    ichert
    0.36
    liğini
    0.36
     <-
    0.36
    され
    0.35
    POSITIVE LOGITS
     than
    0.73
    than
    0.71
    Than
    0.70
     niż
    0.68
     än
    0.64
     decât
    0.62
     Than
    0.59
     než
    0.54
    THAN
    0.48
     daripada
    0.47
    Activations Density 0.050%

    No Known Activations