© 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. 73411
    Prev
    Next
    INDEX
    Explanations

    code and documentation contexts

    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
    探
    -0.81
     caffè
    -0.79
     Vitamina
    -0.76
     עצ
    -0.74
    strcpy
    -0.73
     recessive
    -0.72
     ristoranti
    -0.71
     vecchio
    -0.71
     bronz
    -0.71
    site
    -0.70
    POSITIVE LOGITS
    adaptation
    0.79
    Enumerator
    0.79
     defamation
    0.73
    energies
    0.73
    detailed
    0.73
     enumer
    0.73
    collaboration
    0.73
    udt
    0.73
     Firebase
    0.72
    InteropServices
    0.71
    Activations Density 0.031%

    No Known Activations