© 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. 55741
    Prev
    Next
    INDEX
    Explanations

    programmatic and technical text

    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
     nedir
    -0.89
     ané
    -0.87
    ಿಯ
    -0.86
     berani
    -0.85
     zrozum
    -0.85
     menjal
    -0.83
     mág
    -0.82
    tiker
    -0.82
     douceur
    -0.82
    ㎖
    -0.82
    POSITIVE LOGITS
     awn
    0.85
     Assim
    0.81
    avelength
    0.80
    raszam
    0.77
     نيوز
    0.77
     immoral
    0.76
    Katalog
    0.75
    enero
    0.74
    sipasi
    0.74
     Teilnahme
    0.73
    Activations Density 0.001%

    No Known Activations