Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7734
    Prev
    Next
    INDEX
    Explanations

    MAVSDK and MAVLink protocols

    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
    thereum
    -0.74
    好吃
    -0.73
     suom
    -0.70
     phosphorus
    -0.70
    opard
    -0.68
     alcoholism
    -0.68
     فناوری
    -0.67
    好吃的
    -0.67
     ویتامین
    -0.67
    ूम
    -0.67
    POSITIVE LOGITS
     flight
    1.72
     autopilot
    1.44
     Flight
    1.36
     vehicle
    1.35
     avion
    1.32
     Guidance
    1.30
     navigation
    1.26
     guidance
    1.25
    Flight
    1.18
     Navigation
    1.16
    Activations Density 0.085%

    No Known Activations