© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    bit and related contexts

    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_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
    i
    -1.62
     that
    -1.47
    …’
    -1.45
    IA
    -1.45
     fourrure
    -1.39
     deciso
    -1.38
     lunghi
    -1.38
    
    -1.38
     lontano
    -1.38
    sé
    -1.38
    POSITIVE LOGITS
     $^{\
    2.16
     Когда
    1.76
     $^{
    1.71
     Gründen
    1.61
     ένα
    1.59
    珦
    1.57
     είναι
    1.51
    tovers
    1.47
    zeichnete
    1.46
     Latest
    1.45
    Activations Density 0.015%

    No Known Activations