© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    meaning or alias

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

    explaining or defining

    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
    深深
    0.41
    Ecco
    0.41
    他在
    0.40
    狠狠
    0.40
    сько
    0.39
    ாவில்
    0.39
    Enfin
    0.38
    駋
    0.38
    やっと
    0.38
    Компания
    0.37
    POSITIVE LOGITS
     тобто
    1.17
    including
    1.09
     aka
    1.07
    called
    1.02
    অর্থাৎ
    0.99
    つまり
    0.98
     czyli
    0.95
     অর্থাৎ
    0.94
     AKA
    0.91
    也就是
    0.90
    Activations Density 0.159%

    No Known Activations