© 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. 48261
    Prev
    Next
    INDEX
    Explanations

    morphological, mutation with court

    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
    Realtime
    -0.84
    Mileage
    -0.78
     Reich
    -0.77
    Fld
    -0.76
    ž
    -0.75
    azure
    -0.73
     vuoto
    -0.73
     azure
    -0.73
    drucks
    -0.72
    Flows
    -0.72
    POSITIVE LOGITS
    プロ
    0.83
    Survivors
    0.74
     sulf
    0.68
    FirstOrDefault
    0.67
     androidx
    0.67
    parentNode
    0.67
     đổi
    0.66
    agrad
    0.65
     ceremonies
    0.64
     پس
    0.64
    Activations Density 0.525%

    No Known Activations