© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3351
    Prev
    Next
    INDEX
    Explanations

    Once I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Taw
    1.21
     WIL
    1.08
    칼
    1.01
     Mindanao
    0.99
     Samar
    0.99
    единенных
    0.97
     SWT
    0.97
     Palestina
    0.95
     transversal
    0.95
     karit
    0.95
    POSITIVE LOGITS
     blah
    1.38
    ady
    1.24
    啧
    1.23
     pedig
    1.21
     retarded
    1.20
    睨
    1.20
     fidget
    1.20
    อร์ด
    1.19
    瞅
    1.19
     Cadd
    1.19
    Activations Density 0.141%

    No Known Activations