© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93423
    Prev
    Next
    INDEX
    Explanations

    quests and missions

    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
    DllImport
    -0.90
    Planned
    -0.85
    𝒛
    -0.82
     impinge
    -0.81
     bibl
    -0.80
     Godzilla
    -0.79
     Cem
    -0.79
    Dus
    -0.78
     Niet
    -0.78
     套
    -0.77
    POSITIVE LOGITS
     quest
    2.30
     quests
    2.00
     mission
    2.00
     Quest
    1.64
    Quest
    1.62
    quest
    1.57
     missions
    1.50
     Mission
    1.47
     objectives
    1.45
     task
    1.43
    Activations Density 0.017%

    No Known Activations