© 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-262K
    7. 30397
    Prev
    Next
    INDEX
    Explanations

    * Premise or Requirement

    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_262k_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
    ных
    0.98
     noqa
    0.94
    ренных
    0.92
    ៌
    0.91
    телям
    0.89
    rital
    0.89
    뎅
    0.89
    лены
    0.88
    넬
    0.86
    ренные
    0.86
    POSITIVE LOGITS
    <0x0D>
    0.87
    {}",
    0.80
    >{
    0.78
    بيع
    0.77
    flow
    0.77
    bath
    0.77
     Addiction
    0.77
     fonctionnent
    0.77
    bag
    0.76
    bags
    0.76
    Activations Density 0.000%

    No Known Activations