© 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. 118380
    Prev
    Next
    INDEX
    Explanations

    planning and related activities

    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
    ίδα
    -0.88
    榷
    -0.82
    ühr
    -0.81
    igung
    -0.79
    fera
    -0.78
     Zucchini
    -0.77
     tugas
    -0.76
     模型
    -0.75
    之旅
    -0.75
    veau
    -0.75
    POSITIVE LOGITS
     planning
    7.22
     Planning
    5.41
    planning
    5.38
    Planning
    5.28
     PLANNING
    4.59
     plan
    4.34
     planner
    4.25
     плани
    4.22
     planners
    4.22
     planificación
    4.09
    Activations Density 0.127%

    No Known Activations