© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73316
    Prev
    Next
    INDEX
    Explanations

    formal communication and documentation

    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_10/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
     for
    -2.08
     on
    -1.93
     When
    -1.79
     the
    -1.76
     was
    -1.59
     at
    -1.59
     In
    -1.55
     Usually
    -1.53
    同样的
    -1.40
     to
    -1.37
    POSITIVE LOGITS
     komik
    1.75
     butik
    1.75
     nacht
    1.74
    lllllllll
    1.73
     cirka
    1.72
     you
    1.68
    ==="
    1.68
     grazie
    1.67
     Meksi
    1.64
     engelsk
    1.64
    Activations Density 0.049%

    No Known Activations