© 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. 98199
    Prev
    Next
    INDEX
    Explanations

    whatever you want

    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
    endő
    -0.79
    regex
    -0.75
     investments
    -0.75
     ते
    -0.74
    ábbi
    -0.73
     Gale
    -0.73
    ūsų
    -0.73
     Terry
    -0.72
     probable
    -0.72
    pole
    -0.71
    POSITIVE LOGITS
     want
    1.99
     desired
    1.67
     wanted
    1.63
     wish
    1.61
     pleases
    1.56
    want
    1.52
     Want
    1.45
     quiser
    1.42
     desire
    1.39
    Want
    1.34
    Activations Density 0.029%

    No Known Activations