© 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. 2906
    Prev
    Next
    INDEX
    Explanations

    free play modes

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

    AI models

    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
     Freiburg
    0.42
    
    0.39
     francis
    0.38
    初步
    0.38
    irla
    0.37
     빌
    0.37
     MAY
    0.36
     CHARSET
    0.35
     cytosol
    0.35
     ਤੁ
    0.35
    POSITIVE LOGITS
     По
    0.43
     espí
    0.41
     포
    0.40
    포
    0.39
     Kang
    0.38
    POs
    0.38
     ken
    0.38
     Polym
    0.37
     باہر
    0.37
    पो
    0.37
    Activations Density 0.002%

    No Known Activations