© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115940
    Prev
    Next
    INDEX
    Explanations

    current state described after "Today"

    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
     was
    -1.81
     initially
    -1.80
     zawsze
    -1.79
     previously
    -1.74
     then
    -1.66
     inicialmente
    -1.66
     will
    -1.64
     siempre
    -1.62
     previous
    -1.60
     vždy
    -1.59
    POSITIVE LOGITS
     thanks
    1.40
    thanks
    1.30
    Thanks
    1.20
     still
    1.16
     hardly
    1.14
    days
    1.13
     unrecogn
    1.11
    依然
    1.07
    Mostly
    1.05
    Still
    1.02
    Activations Density 0.082%

    No Known Activations