© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11721
    Prev
    Next
    INDEX
    Explanations

    numbers, money, and gendered roles

    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_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
     borderColor
    1.53
    ាច់
    1.42
     Interess
    1.40
     Thời
    1.40
     ქ
    1.34
    ↵↵↵
    1.31
     気
    1.30
    ोरेशन
    1.29
     其实
    1.29
     Wer
    1.24
    POSITIVE LOGITS
    2
    3.07
    7
    3.00
    1
    2.96
    4
    2.86
    9
    2.86
    8
    2.83
    6
    2.81
    5
    2.76
    3
    2.75
    III
    2.22
    Activations Density 0.368%

    No Known Activations