© 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. 34-GEMMASCOPE-RES-131K
    7. 83682
    Prev
    Next
    INDEX
    Explanations

    text starts, code processes

    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_34/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
     къ
    -0.77
    χυ
    -0.76
     getroffen
    -0.75
    Psycho
    -0.73
     revenir
    -0.72
    loz
    -0.69
    })+\
    -0.69
     fortunately
    -0.69
     ਵਿ
    -0.69
    レール
    -0.68
    POSITIVE LOGITS
     process
    1.62
    process
    1.30
     processus
    1.13
     setTimeout
    1.13
    Process
    1.06
     run
    0.99
     processo
    0.99
    进程
    0.98
     PROCESS
    0.95
     start
    0.94
    Activations Density 0.012%

    No Known Activations