© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    code keywords and identifiers

    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
     процес
    -0.86
    Emotion
    -0.85
    鎂
    -0.81
     enfoque
    -0.78
     resent
    -0.77
    guenos
    -0.77
     vínculo
    -0.77
    Esa
    -0.77
    estation
    -0.77
     hurts
    -0.77
    POSITIVE LOGITS
     this
    1.48
     dette
    1.12
     этом
    1.11
     этот
    1.09
     هذا
    1.05
     Că
    1.02
    this
    1.02
     này
    0.94
    covery
    0.92
     '>
    0.91
    Activations Density 0.065%

    No Known Activations