© 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. 118493
    Prev
    Next
    INDEX
    Explanations

    Startup, Elephant, Retro, numbers

    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
    venue
    -0.85
    टक
    -0.81
     نکنید
    -0.80
    ดย
    -0.76
     satisfying
    -0.76
    useState
    -0.75
    ึกษา
    -0.73
    Attach
    -0.72
     attacked
    -0.72
    vertex
    -0.72
    POSITIVE LOGITS
     roving
    0.81
    lepší
    0.77
    AccessorType
    0.74
    REGIONAL
    0.73
    ône
    0.70
     comp
    0.70
    ecio
    0.69
    lichkeiten
    0.69
     Spawn
    0.69
    ступление
    0.68
    Activations Density 0.015%

    No Known Activations