© 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. 99293
    Prev
    Next
    INDEX
    Explanations

    va or VA followed by word

    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
     pagine
    -0.89
    味が
    -0.81
    ู
    -0.80
    조
    -0.79
     riuscito
    -0.79
     trattato
    -0.79
     時代
    -0.77
     mencionó
    -0.75
     contains
    -0.75
    時代
    -0.73
    POSITIVE LOGITS
     Va
    1.27
    Va
    1.03
     VA
    1.00
     va
    0.94
     entreprises
    0.89
    vau
    0.89
    iation
    0.88
     BENE
    0.86
    הת
    0.83
     BEGINNING
    0.82
    Activations Density 0.022%

    No Known Activations