© 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. 22-GEMMASCOPE-RES-131K
    4. 98583
    Prev
    Next
    INDEX
    Explanations

    citations and headings

    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
     vado
    -1.06
     any
    -1.05
     leves
    -0.93
     olas
    -0.90
     may
    -0.88
     alti
    -0.87
     albu
    -0.87
    ๙
    -0.85
     populi
    -0.85
    先は
    -0.85
    POSITIVE LOGITS
    AGAIN
    0.95
    Indeed
    0.92
     ABSOL
    0.90
    weka
    0.89
     yetu
    0.86
     mężczy
    0.86
     selezion
    0.85
    ῃ
    0.85
     мест
    0.85
     davvero
    0.85
    Activations Density 0.000%

    No Known Activations