© 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. 35942
    Prev
    Next
    INDEX
    Explanations

    method calls with parentheses

    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
     และ
    -0.92
     strikingly
    -0.91
     ludicrous
    -0.90
    ','.
    -0.90
     ridiculously
    -0.85
    chassis
    -0.85
     mens
    -0.85
    NOTAS
    -0.84
     myriad
    -0.84
     amazingly
    -0.84
    POSITIVE LOGITS
     HUGE
    1.07
    Before
    0.99
    There
    0.98
     dazzling
    0.97
     Indigenous
    0.97
    Зри
    0.96
    ліст
    0.96
     Eight
    0.95
     grandparents
    0.93
     blistering
    0.93
    Activations Density 0.006%

    No Known Activations