© 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. 76596
    Prev
    Next
    INDEX
    Explanations

    heist robbery thieves

    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
     stalker
    -0.94
    ereço
    -0.94
     fumar
    -0.78
     Nhân
    -0.76
     abuse
    -0.76
    сили
    -0.75
    poptosis
    -0.75
     Stalker
    -0.73
    PTC
    -0.72
    Pricing
    -0.72
    POSITIVE LOGITS
     heist
    2.53
     thieves
    1.63
     robbery
    1.63
     Heist
    1.56
     thief
    1.52
     Thieves
    1.51
     robbing
    1.51
     theft
    1.46
     stealing
    1.44
     burglary
    1.34
    Activations Density 0.034%

    No Known Activations