© 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. 102625
    Prev
    Next
    INDEX
    Explanations

    data source metadata

    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
    itel
    -0.71
     Succession
    -0.69
    čiu
    -0.68
    ego
    -0.67
    Linking
    -0.67
     Jow
    -0.66
     cag
    -0.65
    Твор
    -0.65
    inode
    -0.65
     Dak
    -0.65
    POSITIVE LOGITS
    itys
    0.85
    cerita
    0.82
    Joshua
    0.76
     formado
    0.76
    ötzlich
    0.73
     ["
    0.73
    mentaux
    0.73
     bohater
    0.71
     upcoming
    0.70
    зе
    0.69
    Activations Density 0.045%

    No Known Activations