© 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. 90469
    Prev
    Next
    INDEX
    Explanations

    phone numbers with area codes

    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
     không
    -1.05
    𝐹
    -0.93
     bedrooms
    -0.87
    ἢ
    -0.86
     carta
    -0.83
    開封
    -0.82
    担当
    -0.82
    eschön
    -0.82
    scaffold
    -0.81
    zdro
    -0.81
    POSITIVE LOGITS
    際には
    0.92
     arvio
    0.85
     Chicago
    0.85
     живет
    0.84
     моск
    0.82
     gouttes
    0.82
     девушка
    0.81
     NYC
    0.81
     New
    0.81
    為に
    0.80
    Activations Density 0.006%

    No Known Activations