© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75611
    Prev
    Next
    INDEX
    Explanations

    point of sale

    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
    jus
    -0.69
    lu
    -0.65
    ៩
    -0.63
    Positioning
    -0.63
     stripped
    -0.63
     siguran
    -0.63
    案内
    -0.63
    binder
    -0.62
     cabelo
    -0.61
    erci
    -0.61
    POSITIVE LOGITS
     point
    3.52
     Point
    2.75
    point
    2.72
    Point
    2.67
     POINT
    2.45
    POINT
    2.17
     точка
    2.09
     punto
    2.03
    getPoint
    1.83
     точку
    1.74
    Activations Density 0.055%

    No Known Activations