© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 14806
    Prev
    Next
    INDEX
    Explanations

    SQL schema or sequence information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insuku
    0.89
     మంది
    0.88
    end
    0.83
     s
    0.81
    тері
    0.81
    ្វី
    0.80
    렛
    0.79
    дий
    0.79
     tự
    0.78
    throughput
    0.78
    POSITIVE LOGITS
    :
    1.05
     misalnya
    0.99
     argentinos
    0.96
     magnétique
    0.95
    ⼀
    0.92
     jedna
    0.91
    игры
    0.91
     mindestens
    0.91
     hermosa
    0.90
     quieras
    0.89
    Activations Density 0.030%

    No Known Activations