© 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. 102846
    Prev
    Next
    INDEX
    Explanations

    carbonite, Han Solo, Leia, version, FREE SHIPPING, Reserve, Detection

    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
    endor
    -0.86
    sv
    -0.79
     äta
    -0.74
     della
    -0.71
     uso
    -0.70
    ipedi
    -0.69
     tom
    -0.67
    PAGER
    -0.67
    Buddy
    -0.67
     sv
    -0.65
    POSITIVE LOGITS
     smuggling
    0.92
    🏹
    0.81
    worship
    0.78
     Han
    0.76
    igraf
    0.75
     smugglers
    0.75
    nerf
    0.75
     slime
    0.73
     sloven
    0.73
     Slime
    0.73
    Activations Density 0.015%

    No Known Activations