© 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. 22-GEMMASCOPE-RES-131K
    7. 35973
    Prev
    Next
    INDEX
    Explanations

    causal conjunctions

    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_22/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
    setAddress
    -0.97
    tilles
    -0.94
     anbef
    -0.94
    пкой
    -0.94
     Ereignisse
    -0.94
     inkluder
    -0.93
    orros
    -0.92
    kömm
    -0.92
     niektor
    -0.91
     リング
    -0.90
    POSITIVE LOGITS
     поскольку
    0.99
     full
    0.86
     via
    0.82
     since
    0.80
     it
    0.79
    .\
    0.79
     благодаря
    0.78
     because
    0.78
     essential
    0.75
    యు
    0.74
    Activations Density 0.020%

    No Known Activations