© 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. 47623
    Prev
    Next
    INDEX
    Explanations

    configuration and code elements

    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
    loadModel
    -0.88
     اعتماد
    -0.87
    셈
    -0.78
    гід
    -0.77
     castro
    -0.76
     esterna
    -0.75
    decla
    -0.74
    bbers
    -0.74
    感動
    -0.73
     cherish
    -0.73
    POSITIVE LOGITS
     ROM
    0.94
    jsp
    0.90
    𝔴
    0.85
    AXI
    0.84
     spic
    0.83
    facet
    0.82
    romeo
    0.82
    epam
    0.81
    ologique
    0.79
     INCOR
    0.79
    Activations Density 0.002%

    No Known Activations