© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98805
    Prev
    Next
    INDEX
    Explanations

    two and half measurements

    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
     вере
    -0.74
     WORK
    -0.71
     THOMPSON
    -0.68
     hundreds
    -0.66
     thousands
    -0.65
    érape
    -0.64
    CDK
    -0.64
     характеристика
    -0.64
    getDoctrine
    -0.64
     dozens
    -0.63
    POSITIVE LOGITS
    ½
    2.95
     ½
    2.63
    half
    1.99
     half
    1.84
    半
    1.84
     setengah
    1.65
    Half
    1.62
    半个
    1.59
    HALF
    1.57
     HALF
    1.48
    Activations Density 0.246%

    No Known Activations