© 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. 75731
    Prev
    Next
    INDEX
    Explanations

    action cameras, recording 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
     public
    -0.84
     senior
    -0.75
    peč
    -0.75
     panel
    -0.73
     hyd
    -0.66
    ėje
    -0.65
     doctor
    -0.65
    entyfik
    -0.65
     Senior
    -0.64
     dise
    -0.63
    POSITIVE LOGITS
     GoPro
    2.94
     cameras
    1.90
     gopro
    1.80
     camera
    1.79
    camera
    1.57
     action
    1.51
    GOP
    1.48
     GOP
    1.48
     HERO
    1.44
     Camera
    1.40
    Activations Density 0.041%

    No Known Activations