© 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. 65764
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming constructs

    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
     =
    -1.90
     ONLY
    -1.86
     ((
    -1.63
     when
    -1.59
    一直
    -1.58
     regularly
    -1.55
     With
    -1.54
     ALWAYS
    -1.53
    !!!!
    -1.52
     regelmäßig
    -1.52
    POSITIVE LOGITS
    櫺
    1.84
    毟
    1.81
    臜
    1.77
    dding
    1.66
     ۸
    1.66
    ㍑
    1.58
    
    1.57
    蟥
    1.55
    interesting
    1.53
    这一
    1.52
    Activations Density 0.061%

    No Known Activations