© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    .py file names

    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
    成为了
    1.12
    ="/
    1.12
     aujourd
    1.10
    ='/
    1.06
     oggi
    1.05
    嘞
    1.04
     gracias
    1.04
     Aujourd
    1.03
     geworden
    1.02
     hoje
    1.01
    POSITIVE LOGITS
     each
    1.28
    Each
    1.17
    each
    1.14
     Each
    1.12
     каждая
    1.06
    separated
    1.03
     每
    1.02
     separated
    1.02
     каждой
    1.01
     каждое
    1.00
    Activations Density 0.125%

    No Known Activations