© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10760
    Prev
    Next
    INDEX
    Explanations

    python main block

    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_22_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
    Ω
    1.25
     Kimmel
    1.23
    ड्रा
    1.19
     Tiro
    1.18
     CMA
    1.13
     Ω
    1.13
     Kapp
    1.13
     Nakh
    1.10
     TRO
    1.09
    <0x85>
    1.09
    POSITIVE LOGITS
     Sik
    1.42
     Token
    1.32
     Manit
    1.28
     Shik
    1.24
     Lar
    1.24
     TOKEN
    1.23
     Scott
    1.22
     Joker
    1.21
    Laravel
    1.21
    Token
    1.20
    Activations Density 1.339%

    No Known Activations