© 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. 9343
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     Nichts
    -1.02
     deberán
    -0.94
     aprovecha
    -0.94
    
    -0.94
    ਢ
    -0.92
     location
    -0.91
     diversité
    -0.90
     puertos
    -0.88
     lápis
    -0.88
     výrob
    -0.85
    POSITIVE LOGITS
    rrrr
    0.93
    ISBN
    0.93
     conector
    0.92
    "">
    0.92
    ників
    0.90
    rrrrr
    0.90
     And
    0.89
    ogueira
    0.88
     ''
    0.85
    أ
    0.85
    Activations Density 0.014%

    No Known Activations