© 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. 57885
    Prev
    Next
    INDEX
    Explanations

    electrostatic discharge

    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
    Jacqueline
    -0.79
    frastructure
    -0.76
     Jacqueline
    -0.76
    itura
    -0.73
     هستید
    -0.69
    ogie
    -0.69
     celebrate
    -0.67
    Alfredo
    -0.66
    ਡ
    -0.66
    rrbracket
    -0.65
    POSITIVE LOGITS
     static
    5.00
    static
    4.47
     Static
    3.88
    Static
    3.75
    STATIC
    3.36
     STATIC
    3.22
    静
    2.84
    静态
    2.78
     electrostatic
    2.73
    statics
    2.58
    Activations Density 0.068%

    No Known Activations