© 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-16K
    7. 9868
    Prev
    Next
    INDEX
    Explanations

    beginner status

    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
    emias
    1.26
    iation
    1.20
    ान
    1.16
    oos
    1.14
    करने
    1.12
    etting
    1.12
    haan
    1.07
    y
    1.07
    ans
    1.06
    an
    1.05
    POSITIVE LOGITS
     フォト
    1.38
     Weeks
    1.28
     库存
    1.24
     雷
    1.22
     直接
    1.20
     hilltop
    1.20
     脚
    1.20
     刺繍
    1.19
     Stich
    1.19
     trece
    1.17
    Activations Density 0.009%

    No Known Activations