© 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. 8394
    Prev
    Next
    INDEX
    Explanations

    html lang

    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
    ụ
    0.91
    الم
    0.87
     ผม
    0.86
    私は
    0.86
    и
    0.85
    ้
    0.84
    iboard
    0.84
     എന്നിവ
    0.82
    𝙛
    0.82
     ഞാൻ
    0.80
    POSITIVE LOGITS
    ことで
    0.89
    ことから
    0.84
    他也
    0.79
    0.78
    তিনি
    0.77
    0.77
     he
    0.75
           
    0.74
    他又
    0.70
     data
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.