© 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. 38303
    Prev
    Next
    INDEX
    Explanations

    divine plans and guidance

    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
     extran
    -0.82
    िक्ष
    -0.78
    rakech
    -0.77
    عنوان
    -0.75
    不得不说
    -0.74
    zeka
    -0.73
    벗
    -0.72
     Needed
    -0.72
     Ayurveda
    -0.71
     viti
    -0.70
    POSITIVE LOGITS
     plans
    1.74
     plan
    1.65
    plans
    1.33
    Plans
    1.23
     Plans
    1.21
    plan
    1.17
     plán
    1.11
     Plan
    1.07
     prosperity
    1.06
    แผน
    1.02
    Activations Density 0.009%

    No Known Activations