© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50100
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    área
    -0.91
    áreas
    -0.88
     farlo
    -0.85
     descubre
    -0.85
    Again
    -0.85
     same
    -0.83
    してない
    -0.83
     elige
    -0.82
    されていない
    -0.82
    していない
    -0.82
    POSITIVE LOGITS
    िता
    0.86
    cado
    0.84
    Knowledge
    0.81
    ꧂
    0.81
    aby
    0.80
     linguri
    0.80
    avad
    0.79
    inars
    0.78
    cillos
    0.78
    mengen
    0.77
    Activations Density 0.063%

    No Known Activations