© 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. 2003
    Prev
    Next
    INDEX
    Explanations

    language boundaries

    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
    هنگ
    -0.80
    ಜ
    -0.79
    thenReturn
    -0.79
     oaths
    -0.78
    父母
    -0.77
     Arabia
    -0.77
    Thinking
    -0.77
    riebe
    -0.77
    rét
    -0.77
     poids
    -0.77
    POSITIVE LOGITS
    こだわり
    0.79
    كى
    0.76
     irgendwo
    0.76
    驚く
    0.76
     mùa
    0.76
    稹
    0.74
     though
    0.73
     appointe
    0.73
     выпол
    0.72
    fra
    0.71
    Activations Density 0.015%

    No Known Activations