© 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. 6050
    Prev
    Next
    INDEX
    Explanations

    concrete construction

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

    structural foundation design

    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
     persön
    0.50
    酒精
    0.47
    颠
    0.46
     संचाल
    0.45
     personnelle
    0.45
    PersonalInfo
    0.44
     चंदन
    0.44
     hủy
    0.44
    轳
    0.44
     angrily
    0.44
    POSITIVE LOGITS
     concrete
    1.39
    混凝土
    1.37
     Concrete
    1.36
    concrete
    1.36
    Concrete
    1.30
     бетон
    1.27
     prefabricated
    1.26
     masonry
    1.22
     beton
    1.20
     prefab
    1.19
    Activations Density 0.237%

    No Known Activations