© 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. 116536
    Prev
    Next
    INDEX
    Explanations

    tokens starting common phrases

    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
     piensan
    -0.82
     fá
    -0.81
     Deshalb
    -0.80
     carelessness
    -0.80
    そういう
    -0.80
     pensaba
    -0.79
     despertar
    -0.79
    一起去
    -0.77
    而不是
    -0.77
    Bộ
    -0.77
    POSITIVE LOGITS
    Refer
    0.98
    melons
    0.96
     REFER
    0.93
    ִּי
    0.92
     frito
    0.92
     LETTERS
    0.88
     MILLION
    0.87
    refer
    0.86
    😹
    0.85
     LADY
    0.85
    Activations Density 0.006%

    No Known Activations