© 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. 555
    Prev
    Next
    INDEX
    Explanations

    coordinate systems and projection

    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
     forState
    -0.76
     Positive
    -0.74
     translated
    -0.73
     Rate
    -0.71
     grasa
    -0.70
     translation
    -0.70
     English
    -0.69
     rainha
    -0.69
     hair
    -0.68
     pseudo
    -0.68
    POSITIVE LOGITS
    projection
    1.77
     projection
    1.77
    Projection
    1.59
     Projection
    1.49
     projections
    1.45
     Projections
    1.34
    proj
    1.28
    投影
    1.23
     proj
    1.19
     coordinate
    1.17
    Activations Density 0.035%

    No Known Activations