© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 47
    Prev
    Next
    INDEX
    Explanations

    do you or could you

    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
    有个
    0.79
    这个
    0.79
     literally
    0.78
     stealing
    0.77
    无
    0.76
     something
    0.75
    有一个
    0.75
     estimates
    0.74
    不知道
    0.74
    个
    0.73
    POSITIVE LOGITS
     elő
    1.54
     ilyen
    1.53
     nagyon
    1.53
     különböző
    1.51
     szabály
    1.49
     új
    1.49
     idő
    1.48
     köz
    1.48
     erő
    1.46
     által
    1.46
    Activations Density 0.204%

    No Known Activations