© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8918
    Prev
    Next
    INDEX
    Explanations

    ordered, provided, or described

    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_13_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
     봤
    1.57
    性和
    1.33
     voglio
    1.30
     igneous
    1.30
    人了
    1.27
     andRow
    1.26
    цията
    1.26
    해도
    1.26
     けど
    1.26
     казиносу
    1.25
    POSITIVE LOGITS
    .
    1.01
     ("
    0.96
    ert
    0.94
     zone
    0.94
     (
    0.93
     (“
    0.93
    ,
    0.92
     Barang
    0.92
    。
    0.91
     frame
    0.90
    Activations Density 0.000%

    No Known Activations