© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48500
    Prev
    Next
    INDEX
    Explanations

    'do' commands and prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whopping
    -0.86
    颇
    -0.86
    ucción
    -0.79
    ্ট
    -0.79
     選
    -0.77
    ៏
    -0.77
     लि
    -0.77
    徳島
    -0.76
    aww
    -0.75
    uban
    -0.75
    POSITIVE LOGITS
    зиру
    0.82
    colades
    0.77
    尚未
    0.76
    Ű
    0.76
    albeit
    0.75
    车辆
    0.75
     одежду
    0.75
    zeu
    0.74
    LLA
    0.70
    ющая
    0.69
    Activations Density 0.044%

    No Known Activations