© 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. 115875
    Prev
    Next
    INDEX
    Explanations

    Batch Normalization

    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
    offsetWidth
    -0.79
     forKey
    -0.78
    OSPH
    -0.78
    ɩ
    -0.78
     Newport
    -0.75
     Sita
    -0.75
     domicili
    -0.74
     Heidegger
    -0.74
     година
    -0.73
    voyance
    -0.73
    POSITIVE LOGITS
     normalization
    1.80
    normalization
    1.61
    Normalization
    1.54
    norm
    1.53
     BN
    1.45
     norm
    1.45
    Norm
    1.43
     Normalize
    1.38
     Batch
    1.33
     normalize
    1.32
    Activations Density 0.014%

    No Known Activations