© 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. 86971
    Prev
    Next
    INDEX
    Explanations

    existence or presence

    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
    ものです
    -1.20
    iramente
    -1.09
     cdti
    -1.09
    كذا
    -1.07
    |};
    -0.98
    urlaub
    -0.92
    もので
    -0.92
    程度上
    -0.91
     насеља
    -0.90
    izzazione
    -0.88
    POSITIVE LOGITS
     there
    8.56
    There
    5.16
     есть
    4.84
     There
    4.41
     هناك
    4.09
    there
    4.03
     gibt
    3.83
    Есть
    3.53
     există
    3.50
     exists
    3.36
    Activations Density 0.022%

    No Known Activations