© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1481
    Prev
    Next
    INDEX
    Explanations

    let me know

    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_17_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
     abi
    0.97
     vun
    0.93
     ils
    0.93
    ণ
    0.89
    heder
    0.82
    €.
    0.82
     ident
    0.82
    €
    0.80
     bess
    0.80
     Türkçe
    0.79
    POSITIVE LOGITS
     loose
    1.57
    loose
    1.45
     byg
    1.32
    ting
    1.28
    Loose
    1.16
    鍝
    1.12
    ras
    1.10
     imaginations
    1.09
    itia
    1.08
     go
    1.07
    Activations Density 0.122%

    No Known Activations