© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6001
    Prev
    Next
    INDEX
    Explanations

    specific terms or statements

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

    classification categories and technical aspects

    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
     enfim
    0.48
    基本的な
    0.42
     whatnot
    0.41
     چند
    0.41
     hatta
    0.41
     বেশ
    0.40
    ත
    0.40
     quinze
    0.40
     deje
    0.38
     generell
    0.38
    POSITIVE LOGITS
    を作成
    0.50
    ='
    0.50
    :
    0.50
     cards
    0.48
    ="
    0.47
    6
    0.46
    :"
    0.45
     technique
    0.45
    式
    0.45
     codes
    0.45
    Activations Density 0.623%

    No Known Activations