© 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. 58255
    Prev
    Next
    INDEX
    Explanations

    copyright notices, licenses, version

    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
    Indeed
    -0.84
    Newcastle
    -0.72
    ogos
    -0.71
    當天
    -0.71
     bojo
    -0.71
    hålla
    -0.69
    لاج
    -0.68
     опера
    -0.68
     руковод
    -0.67
    ultuous
    -0.67
    POSITIVE LOGITS
    🇻
    0.90
    VC
    0.87
     VHS
    0.82
     virginia
    0.78
     VIC
    0.75
     vicar
    0.74
     svm
    0.74
    Montag
    0.74
     DMV
    0.74
     duck
    0.73
    Activations Density 0.025%

    No Known Activations