© 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. 10-GEMMASCOPE-RES-131K
    7. 130368
    Prev
    Next
    INDEX
    Explanations

    font awesome icons

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags icon‐related identifier tokens in code (e.g. FontAwesome class names like “chevron‐up,” “play‐circle,” or drawable icon names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -1.90
     Inſ
    -1.44
     augusti
    -1.36
     ananas
    -1.34
    ‘‘
    -1.32
     pantal
    -1.31
     kome
    -1.30
    也是
    -1.27
     vanille
    -1.26
     heller
    -1.23
    POSITIVE LOGITS
     Drittan
    1.52
     schönsten
    1.50
    ですし
    1.44
     feinen
    1.43
     inicios
    1.41
     oči
    1.39
     reichlich
    1.38
     gewöhnlich
    1.34
     začet
    1.34
     båda
    1.31
    Activations Density 0.002%

    No Known Activations