© 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. 54051
    Prev
    Next
    INDEX
    Explanations

    knee or knees

    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
     Fintech
    -0.79
     endoc
    -0.78
     després
    -0.75
     परि
    -0.71
    写真を撮
    -0.69
    ͕
    -0.69
     powdery
    -0.68
    Paco
    -0.68
     chez
    -0.68
     shrinkage
    -0.67
    POSITIVE LOGITS
     knees
    4.41
     knee
    3.33
    kne
    3.13
     kneel
    3.08
     kneeling
    3.05
     Kne
    2.98
     knelt
    2.81
     kne
    2.69
    knee
    2.69
     Knee
    2.67
    Activations Density 0.027%

    No Known Activations