© 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. 12-GEMMASCOPE-2-RES-16K
    7. 495
    Prev
    Next
    INDEX
    Explanations

    I am, I believe

    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_12_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
    ن
    2.02
    ли
    1.88
    可以
    1.55
    ת
    1.44
    ש
    1.38
    ند
    1.34
    ل
    1.34
    le
    1.32
    م
    1.30
    و
    1.27
    POSITIVE LOGITS
    ritis
    1.00
    gesamt
    0.97
     heaped
    0.96
    stood
    0.95
    erweise
    0.94
     নিজেও
    0.92
    いた
    0.92
    нь
    0.91
     అయితే
    0.89
     awful
    0.88
    Activations Density 0.656%

    No Known Activations