© 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. 93751
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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
     Mut
    -0.71
    ⁵
    -0.69
    пали
    -0.69
     Mason
    -0.69
    Talks
    -0.66
    Tien
    -0.66
    tette
    -0.65
     configure
    -0.65
     Transition
    -0.64
     déf
    -0.64
    POSITIVE LOGITS
    ቱ
    0.77
    cznych
    0.70
    upan
    0.68
     đậu
    0.66
     successors
    0.66
     successor
    0.66
    焯
    0.65
     raccomand
    0.64
    downloader
    0.63
    轼
    0.63
    Activations Density 0.063%

    No Known Activations