© 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. 92448
    Prev
    Next
    INDEX
    Explanations

    status bar

    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
    Japon
    -0.89
    νή
    -0.81
    ugd
    -0.80
    Chairperson
    -0.79
    abilirsiniz
    -0.79
    팡
    -0.78
    بینی
    -0.78
     perspek
    -0.77
     japon
    -0.74
    こんにちは
    -0.72
    POSITIVE LOGITS
     status
    1.23
     Status
    1.15
     bar
    1.13
    setStatus
    1.04
     bars
    1.03
     STATUS
    0.99
    StatusBar
    0.97
     dark
    0.94
    STATUS
    0.93
     hides
    0.92
    Activations Density 0.019%

    No Known Activations