© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12390
    Prev
    Next
    INDEX
    Explanations

    to match conditions or statements

    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
    \})
    0.83
    ים
    0.81
    ో
    0.78
    }\}
    0.76
    adə
    0.76
    esthetics
    0.75
    ك
    0.74
    ወስ
    0.73
    ઓમાં
    0.73
     સરળ
    0.73
    POSITIVE LOGITS
     objeto
    0.83
     Ответ
    0.80
     سامنا
    0.77
     Cyst
    0.76
     Olaf
    0.75
     continuamos
    0.75
    全て
    0.74
     objetivo
    0.74
     GmbH
    0.74
     ООО
    0.74
    Activations Density 0.000%

    No Known Activations