© 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. 70146
    Prev
    Next
    INDEX
    Explanations

    floppy disk

    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
     jugend
    -0.70
    ſt
    -0.68
    tter
    -0.68
     Antônio
    -0.68
     durchschnitt
    -0.67
    athic
    -0.66
    孤独
    -0.65
     IPTV
    -0.65
     HDMI
    -0.65
     мной
    -0.64
    POSITIVE LOGITS
     floppy
    1.73
     disk
    1.30
     Disk
    1.23
     Flo
    1.18
    Disk
    1.16
     disks
    1.14
    disk
    1.10
    DISK
    1.05
    flo
    1.02
    fdc
    1.02
    Activations Density 0.036%

    No Known Activations