© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1242
    Prev
    Next
    INDEX
    Explanations

    np*

    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_17_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
     plastic
    1.03
     PIN
    0.91
     synonym
    0.90
    *;
    0.90
     or
    0.85
    .;
    0.84
     still
    0.83
     =",
    0.82
     kiwi
    0.82
     PCR
    0.79
    POSITIVE LOGITS
    哪怕
    1.71
    即便
    1.60
    就算是
    1.57
    虽然
    1.48
    尽管
    1.46
    即使
    1.43
     навіть
    1.42
    事实上
    1.42
    แม้
    1.40
     даже
    1.38
    Activations Density 0.022%

    No Known Activations