© 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. 22-GEMMASCOPE-RES-131K
    4. 92930
    Prev
    Next
    INDEX
    Explanations

    quoted speech start

    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_22/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
     undeniably
    -1.83
     burgeoning
    -1.81
     exquisitely
    -1.79
     with
    -1.71
    langkah
    -1.69
     supremely
    -1.66
     Putting
    -1.60
     reinforces
    -1.59
    langsung
    -1.59
     Excellent
    -1.59
    POSITIVE LOGITS
     I
    2.14
     it
    2.13
     และ
    1.94
     you
    1.91
     we
    1.88
     they
    1.79
     then
    1.77
    GRAFÍA
    1.73
     estabelec
    1.73
     haupts
    1.72
    Activations Density 0.002%

    No Known Activations