© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91832
    Prev
    Next
    INDEX
    Explanations

    computers and devices

    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
    collants
    -0.79
     pulsante
    -0.77
     deberían
    -0.77
     fiscale
    -0.76
    combobox
    -0.75
    퀀
    -0.75
    BOA
    -0.75
    鈽
    -0.74
     漆
    -0.74
     QoS
    -0.74
    POSITIVE LOGITS
     computers
    4.19
     laptop
    3.80
     computer
    3.70
     laptops
    3.41
     devices
    2.91
    computer
    2.77
    computers
    2.75
     Computers
    2.72
     smartphones
    2.63
     smartphone
    2.58
    Activations Density 0.241%

    No Known Activations