© 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. 31473
    Prev
    Next
    INDEX
    Explanations

    slack A Q % / if

    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
     superbly
    -0.96
     epitom
    -0.89
     undeniably
    -0.87
    pagest
    -0.87
     demur
    -0.87
     substantially
    -0.85
    🫤
    -0.83
     oftentimes
    -0.82
    engkapi
    -0.81
     consistently
    -0.81
    POSITIVE LOGITS
    Michigan
    0.91
     marié
    0.89
     Michigan
    0.88
     arrogant
    0.85
    revealed
    0.81
     gorgeous
    0.81
     garan
    0.81
    Schüler
    0.80
     breathtaking
    0.78
     apparente
    0.78
    Activations Density 0.029%

    No Known Activations