© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    Okay, I understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itati
    0.65
    sü
    0.65
    ác
    0.64
     વડે
    0.64
     സഹ
    0.64
     despl
    0.63
     李
    0.63
     потра
    0.63
    λεύ
    0.63
    éder
    0.63
    POSITIVE LOGITS
    टकों
    0.63
     eateries
    0.62
     public
    0.57
     dining
    0.57
    thione
    0.57
    kin
    0.57
     running
    0.56
    ຮ
    0.55
     কামান
    0.55
     Running
    0.54
    Activations Density 0.189%

    No Known Activations