© 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. 9829
    Prev
    Next
    INDEX
    Explanations

    en/latest/ documentation

    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
    require
    1.05
     ataupun
    0.94
    都需要
    0.90
     或者
    0.87
    或是
    0.87
     مثلا
    0.86
     they
    0.86
    皆
    0.85
    一个个
    0.84
     требуют
    0.84
    POSITIVE LOGITS
     рассказал
    1.62
     commented
    1.58
     falou
    1.57
     explains
    1.40
     рассказывает
    1.38
     comentó
    1.37
     говорит
    1.37
     habló
    1.36
    comment
    1.33
     told
    1.33
    Activations Density 0.079%

    No Known Activations