© 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. 60684
    Prev
    Next
    INDEX
    Explanations

    no such file or directory

    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
     secondly
    -0.90
    ો
    -0.81
    ὢ
    -0.80
     galley
    -0.78
     therap
    -0.75
    シルバー
    -0.71
    银
    -0.71
    銀
    -0.70
    edad
    -0.69
     Constru
    -0.69
    POSITIVE LOGITS
     Ο
    0.75
    showMessage
    0.73
    Mara
    0.70
    Blick
    0.69
     Ethiopian
    0.68
     savez
    0.68
     Orr
    0.68
     messages
    0.67
    förder
    0.67
    榭
    0.66
    Activations Density 0.048%

    No Known Activations