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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110475
    Prev
    Next
    INDEX
    Explanations

    river names

    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
     verdad
    -0.84
    त्ति
    -0.79
     depender
    -0.79
     Bev
    -0.79
     Oceanography
    -0.78
    Woodland
    -0.77
    OrderDetails
    -0.77
     réalis
    -0.75
     viên
    -0.75
    sslich
    -0.75
    POSITIVE LOGITS
     forks
    1.16
     Mississippi
    1.04
     fork
    1.02
     branch
    1.02
     Fork
    1.00
    Fork
    0.99
     branches
    0.97
    fork
    0.92
     east
    0.91
     head
    0.89
    Activations Density 0.036%

    No Known Activations