© 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. 80726
    Prev
    Next
    INDEX
    Explanations

    numbers and units for height

    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
    Var
    -0.75
     Var
    -0.75
     Kne
    -0.71
     действия
    -0.71
     four
    -0.67
     Yup
    -0.66
     MED
    -0.66
     intptr
    -0.66
     wreath
    -0.66
     program
    -0.65
    POSITIVE LOGITS
     growth
    1.14
    身長
    1.13
     height
    1.08
    growth
    0.92
    Growth
    0.91
     Growth
    0.90
     tall
    0.87
    Incompatible
    0.85
     būtų
    0.84
     рост
    0.84
    Activations Density 0.015%

    No Known Activations