© 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. 91169
    Prev
    Next
    INDEX
    Explanations

    gold rush mining

    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
    kkar
    -0.69
     necro
    -0.69
     Kyr
    -0.68
     كره
    -0.68
    bulaire
    -0.68
    btnSave
    -0.67
    IRM
    -0.66
    biotic
    -0.66
    ждане
    -0.66
    vanju
    -0.64
    POSITIVE LOGITS
     gold
    1.95
    gold
    1.70
     Gold
    1.50
    Gold
    1.49
     prospecting
    1.46
    GOLD
    1.39
    淘
    1.38
     strike
    1.38
     rushes
    1.38
     золото
    1.37
    Activations Density 0.018%

    No Known Activations