© 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. 49794
    Prev
    Next
    INDEX
    Explanations

    www and android prefixes

    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
     costuma
    -0.95
     connue
    -0.86
     suivi
    -0.85
    ulti
    -0.82
    Interop
    -0.82
     seront
    -0.82
    expr
    -0.81
     SPAIN
    -0.81
    циями
    -0.81
     وق
    -0.80
    POSITIVE LOGITS
     extinción
    1.02
    sudoku
    0.90
    salomon
    0.89
    FLP
    0.85
    LAUGHTER
    0.85
     Familienname
    0.85
     Tämä
    0.85
    alexander
    0.83
     abbreviation
    0.83
     மற்ற
    0.81
    Activations Density 0.024%

    No Known Activations