© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38219
    Prev
    Next
    INDEX
    Explanations

    #include lines

    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
    ėje
    -0.78
    wx
    -0.77
    ución
    -0.77
     Tribunal
    -0.75
     Fleur
    -0.74
    搞笑
    -0.73
     fabricant
    -0.73
    fahrzeug
    -0.72
    autés
    -0.72
     sparse
    -0.72
    POSITIVE LOGITS
    addError
    0.85
     disk
    0.85
    Créditos
    0.82
     Disk
    0.74
    Procedimento
    0.73
    Pgina
    0.72
    اتب
    0.71
    zam
    0.69
    pozycji
    0.68
    lastic
    0.68
    Activations Density 0.016%

    No Known Activations