© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100972
    Prev
    Next
    INDEX
    Explanations

    looking for a

    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
     myriad
    -1.70
     двумя
    -1.68
     самы
    -1.64
    ところが
    -1.63
    
    -1.59
     sogen
    -1.59
    内容は
    -1.55
     dangers
    -1.55
    
    -1.53
    
    -1.51
    POSITIVE LOGITS
     to
    2.23
     if
    1.98
     but
    1.76
    </h1>
    1.75
     when
    1.72
     which
    1.66
     after
    1.58
     has
    1.53
     Therefore
    1.51
    亟
    1.45
    Activations Density 0.044%

    No Known Activations