© 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. 25868
    Prev
    Next
    INDEX
    Explanations

    html table elements

    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
    ApiModel
    -0.86
    麸
    -0.82
    documentclass
    -0.81
    ]),
    -0.81
    Читати
    -0.81
    BURGH
    -0.80
    🔐
    -0.79
     posh
    -0.79
    ("--
    -0.77
    ##############
    -0.77
    POSITIVE LOGITS
     table
    0.77
    GRAFÍA
    0.76
    ığın
    0.74
    Mittel
    0.73
     now
    0.73
    まり
    0.72
     Даже
    0.71
    捲
    0.69
    GRAFIA
    0.69
     wpły
    0.68
    Activations Density 0.007%

    No Known Activations