© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11829
    Prev
    Next
    INDEX
    Explanations

    resistors and capacitors

    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
    omation
    -0.95
     Sous
    -0.91
     PUBL
    -0.87
    niques
    -0.86
    胥
    -0.83
     Journalist
    -0.82
     олив
    -0.81
    OuterAlt
    -0.81
    damento
    -0.79
    وظ
    -0.78
    POSITIVE LOGITS
     resistors
    3.16
     resistor
    3.11
     Resist
    2.69
     capacitors
    2.31
    Resist
    2.30
     capacitor
    2.16
    resist
    2.11
     resist
    2.03
     resistance
    1.83
     рези
    1.81
    Activations Density 0.124%

    No Known Activations