© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48863
    Prev
    Next
    INDEX
    Explanations

    nonparametric / non

    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
     Tala
    -0.78
    rebro
    -0.73
     doucement
    -0.72
     codes
    -0.71
    lossary
    -0.71
    stellen
    -0.69
     pillows
    -0.69
    wochen
    -0.69
     protesters
    -0.69
    athy
    -0.68
    POSITIVE LOGITS
     parametric
    3.97
    parametric
    3.27
     Parametric
    3.25
    ametric
    1.95
    Par
    1.86
     PARAM
    1.77
     parameterized
    1.62
     parametri
    1.52
     parame
    1.48
    parametri
    1.48
    Activations Density 0.097%

    No Known Activations