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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8868
    Prev
    Next
    INDEX
    Explanations

    Ask and get

    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
     Financ
    1.00
     delivering
    1.00
    慷
    0.97
    当前的
    0.97
    কাত
    0.96
    تقديم
    0.95
    当前
    0.95
     Delivering
    0.94
     అందించ
    0.94
    くれました
    0.93
    POSITIVE LOGITS
     memos
    0.92
     conc
    0.92
     late
    0.87
     Eve
    0.86
    ில
    0.86
    글
    0.86
    ѣ
    0.85
    iya
    0.84
    피
    0.84
    domin
    0.83
    Activations Density 0.000%

    No Known Activations