© 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. 248
    Prev
    Next
    INDEX
    Explanations

    ASIL B

    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
    फिकेशन
    0.88
     уровнем
    0.86
    霾
    0.81
    ంగా
    0.80
    zony
    0.79
     attentions
    0.78
     Administrat
    0.78
    ख्ती
    0.78
     ellips
    0.77
    щены
    0.74
    POSITIVE LOGITS
    a
    1.13
    s
    0.98
    ب
    0.92
    𝗲
    0.92
     berkaitan
    0.88
    க
    0.81
    I
    0.80
    𝗮
    0.80
    並且
    0.79
    सँग
    0.78
    Activations Density 0.000%

    No Known Activations