© 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. 34-GEMMASCOPE-RES-131K
    7. 31526
    Prev
    Next
    INDEX
    Explanations

    financial codes 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_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
    gerufen
    -0.83
     gefunden
    -0.81
     desarrollan
    -0.77
    eming
    -0.77
     provocando
    -0.76
     formando
    -0.75
    啱
    -0.75
     isoliert
    -0.75
    indirect
    -0.74
     estrenar
    -0.74
    POSITIVE LOGITS
    torch
    0.82
     even
    0.82
     якщо
    0.79
    chrom
    0.79
    tedì
    0.79
    constru
    0.78
    甚至
    0.77
     Telekom
    0.77
     women
    0.76
     REV
    0.76
    Activations Density 0.003%

    No Known Activations