© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13074
    Prev
    Next
    INDEX
    Explanations

    OS commands and paths

    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_7_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
    vious
    1.48
    ؎
    1.48
     Ud
    1.40
     például
    1.39
     obiect
    1.39
     scritt
    1.39
     erwäh
    1.38
     erklärte
    1.37
     nomi
    1.37
     historii
    1.37
    POSITIVE LOGITS
     !!
    1.48
     李
    1.48
    ด
    1.45
    ..
    1.43
    .,
    1.43
    李
    1.40
    ..!
    1.39
    Opacity
    1.35
     !!!
    1.35
     %
    1.34
    Activations Density 0.039%

    No Known Activations