© 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. 9780
    Prev
    Next
    INDEX
    Explanations

    React imports and hooks

    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
     After
    -1.59
     only
    -1.54
     might
    -1.51
     will
    -1.48
     those
    -1.48
     to
    -1.45
     not
    -1.44
     Before
    -1.44
     both
    -1.42
     while
    -1.42
    POSITIVE LOGITS
     maniere
    1.68
     unbelievably
    1.38
    licherweise
    1.37
     wondrous
    1.35
    Including
    1.34
     startling
    1.34
    ㉖
    1.34
     Dinas
    1.32
    
    1.31
     gratuite
    1.30
    Activations Density 0.001%

    No Known Activations