© 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. 37566
    Prev
    Next
    INDEX
    Explanations

    Australian cities and places

    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
     kuid
    0.82
     daarom
    0.78
     alcun
    0.75
     sillons
    0.72
     Specification
    0.70
     excès
    0.70
    س
    0.69
    ਟਰ
    0.68
     납
    0.68
     därför
    0.68
    POSITIVE LOGITS
    ate
    0.94
    Clos
    0.92
    zmq
    0.89
    Checkpoint
    0.85
     кажется
    0.82
    didn
    0.79
    ada
    0.79
    ato
    0.79
    ginx
    0.79
     ситуацию
    0.79
    Activations Density 0.000%

    No Known Activations