© 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. 55778
    Prev
    Next
    INDEX
    Explanations

    finding jewelry, vacation rental, announcement, question, explanation, copyright

    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
    ﷲ
    -0.83
    haltens
    -0.79
     numerous
    -0.78
     Multivariate
    -0.77
     Profiling
    -0.77
     profiling
    -0.76
    Pho
    -0.75
     bereits
    -0.73
     yana
    -0.71
    ácidos
    -0.71
    POSITIVE LOGITS
     装着
    0.93
    ISHOP
    0.93
    ὸν
    0.91
    OPERATOR
    0.89
     התח
    0.87
    COS
    0.86
     MeV
    0.86
    shirts
    0.85
    gasse
    0.85
    sione
    0.84
    Activations Density 0.003%

    No Known Activations