© 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. 66250
    Prev
    Next
    INDEX
    Explanations

    header or title separators

    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
    Nikon
    -0.96
    Vrij
    -0.88
    Stell
    -0.87
     bep
    -0.83
    Elek
    -0.83
     SPONS
    -0.81
     crin
    -0.81
    ƨ
    -0.80
     TEACHING
    -0.80
     sovi
    -0.79
    POSITIVE LOGITS
     header
    1.22
    header
    1.13
    Header
    1.05
    سم
    0.88
     Header
    0.88
    要点
    0.81
    Metrics
    0.79
    Title
    0.76
    HEADER
    0.75
    Style
    0.74
    Activations Density 0.000%

    No Known Activations