© 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. 65480
    Prev
    Next
    INDEX
    Explanations

    foreign languages and technical terms

    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
     without
    -0.78
    aconda
    -0.77
     kvad
    -0.75
     Vec
    -0.74
     whose
    -0.74
    Vec
    -0.74
    我家
    -0.73
    閏
    -0.72
    vč
    -0.72
    TEntity
    -0.70
    POSITIVE LOGITS
     températures
    0.90
     virtud
    0.84
     colossal
    0.84
     şun
    0.83
     monstrous
    0.81
     vooral
    0.80
     discu
    0.78
     gigantic
    0.77
     vijf
    0.76
    selves
    0.74
    Activations Density 0.001%

    No Known Activations