© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31099
    Prev
    Next
    INDEX
    Explanations

    code and programming keywords

    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
     mirth
    -0.95
     entsprechend
    -0.90
     zunächst
    -0.90
    良いです
    -0.90
     entspre
    -0.85
    jsko
    -0.83
     различ
    -0.81
    НИК
    -0.81
     demais
    -0.81
     entsprechende
    -0.80
    POSITIVE LOGITS
    =("
    1.02
    beforeEach
    0.94
    κος
    0.93
    =('
    0.93
    Zubereitung
    0.91
     verduras
    0.90
     (){
    0.88
    topRight
    0.88
    ();}
    0.87
    resultMap
    0.86
    Activations Density 0.130%

    No Known Activations