© 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. 48256
    Prev
    Next
    INDEX
    Explanations

    treasure hunt, chests, troves

    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
     decorativo
    -0.86
     entusias
    -0.82
     crushes
    -0.79
    幸せ
    -0.73
     redwood
    -0.73
     crédit
    -0.73
     Calder
    -0.73
    statics
    -0.72
    幸福
    -0.71
     shreds
    -0.71
    POSITIVE LOGITS
     trove
    2.14
     chest
    1.77
     hunt
    1.58
     chests
    1.46
    chest
    1.35
    Chest
    1.30
     Chest
    1.27
     tro
    1.27
     Tro
    1.23
    treas
    1.22
    Activations Density 0.017%

    No Known Activations