© 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. 67715
    Prev
    Next
    INDEX
    Explanations

    following specific words

    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
    persian
    -1.02
    بيل
    -1.01
    สำหรับ
    -0.98
     Potencia
    -0.96
    饽
    -0.93
    stination
    -0.92
    verbal
    -0.90
     Tecnología
    -0.89
     fröh
    -0.88
    CloseOperation
    -0.88
    POSITIVE LOGITS
     seguire
    0.90
    cov
    0.90
    で購入
    0.88
     previous
    0.85
    w
    0.84
    ativ
    0.83
    those
    0.82
    only
    0.82
    Etter
    0.81
     ayant
    0.81
    Activations Density 0.314%

    No Known Activations