© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8686
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
     тях
    0.96
    atórios
    0.95
    ایک
    0.95
    etição
    0.94
    Ģ
    0.94
     сте
    0.93
     језик
    0.92
    шта
    0.90
    стной
    0.89
    <0xF1>
    0.89
    POSITIVE LOGITS
     park
    1.17
     sab
    1.12
     NPS
    1.11
     Dile
    1.10
     navy
    1.08
     democratic
    1.07
     Derby
    1.06
     NDA
    1.05
     endeavor
    1.05
     july
    1.04
    Activations Density 0.198%

    No Known Activations