© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2390
    Prev
    Next
    INDEX
    Explanations

    units of data and specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     pensiero
    1.30
     pensée
    1.18
    Marketing
    1.17
    Monument
    1.15
    思维
    1.14
    Toward
    1.13
    
    1.11
    观
    1.09
    웡
    1.08
    డాది
    1.08
    POSITIVE LOGITS
     lev
    1.03
    с
    0.95
     все
    0.93
    или
    0.91
     prav
    0.90
     bajas
    0.90
    ี่
    0.89
    ӓ
    0.89
     並
    0.89
    olan
    0.89
    Activations Density 0.001%

    No Known Activations