© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4966
    Prev
    Next
    INDEX
    Explanations

    numbers followed by sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ؟!
    0.79
     dibandingkan
    0.77
    🙃
    0.68
     fontSize
    0.68
     ≠
    0.68
     !==
    0.67
    !==
    0.66
     jäl
    0.65
     slechts
    0.65
     '_'
    0.64
    POSITIVE LOGITS
    協助
    0.99
    协助
    0.94
    帮忙
    0.87
     enables
    0.87
     помогает
    0.86
    用来
    0.80
     umożliw
    0.79
     помогают
    0.79
     helps
    0.79
    ช่วย
    0.77
    Activations Density 0.926%

    No Known Activations