© 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. 50135
    Prev
    Next
    INDEX
    Explanations

    unicode copyright utf

    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
    鳃
    -0.77
     findViewById
    -0.77
    れたら
    -0.76
    CLASSIFIED
    -0.75
     unjustified
    -0.75
     chegar
    -0.74
     ρ
    -0.73
    OBJECT
    -0.73
     upholding
    -0.73
     долго
    -0.73
    POSITIVE LOGITS
    mité
    0.93
     clearly
    0.92
    ophile
    0.82
    unten
    0.82
     those
    0.81
     nearly
    0.81
     practically
    0.76
    pecting
    0.75
    Ngo
    0.74
    甥
    0.73
    Activations Density 0.012%

    No Known Activations