© 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. 10-GEMMASCOPE-RES-131K
    7. 1313
    Prev
    Next
    INDEX
    Explanations

    creating code operations

    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_10/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
     ppl
    -2.17
    ９
    -2.11
    ൾ
    -2.08
    ，
    -2.02
    「
    -1.97
     VILLA
    -1.95
    Following
    -1.92
     fulf
    -1.91
    When
    -1.89
    Adding
    -1.89
    POSITIVE LOGITS
     they
    2.80
    柺
    2.67
     “
    2.61
     (“
    2.52
    .”
    1.98
    
    1.97
     berbagai
    1.92
    อย่างไร
    1.92
    ญี่ป
    1.91
    桴
    1.90
    Activations Density 0.000%

    No Known Activations