© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1068
    Prev
    Next
    INDEX
    Explanations

    structure classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
    キャンペーン
    0.75
     retiro
    0.75
     ওয়ালপেপার
    0.72
    णिमा
    0.71
     oprav
    0.69
     ক্ষমা
    0.68
    ኝ
    0.67
    వలం
    0.67
    疼
    0.67
     Campaigns
    0.66
    POSITIVE LOGITS
     structure
    4.98
    structure
    4.65
     Structure
    4.57
    结构
    4.57
     estructura
    4.39
     STRUCTURE
    4.38
    Structure
    4.38
     structures
    4.31
     strukt
    4.19
     struktur
    4.17
    Activations Density 1.560%

    No Known Activations